© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36397
    Prev
    Next
    INDEX
    Explanations

    information related to weapons, military capabilities, and security issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.22
    1.1%
    481
    +0.15
    0.7%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.22
    0.35
    255
    +0.15
    0.12
    481
    +0.10
    0.35
    Negative Logits
    abase
    -0.79
    ©¶æ¥µ
    -0.76
    oyal
    -0.70
    irlfriend
    -0.69
    itely
    -0.66
    iaries
    -0.66
    »Ĵ
    -0.64
    umeric
    -0.61
    VOL
    -0.59
    ãĤ¢ãĥ«
    -0.59
    POSITIVE LOGITS
     highways
    0.83
    interstitial
    0.80
     bridges
    0.72
    monary
    0.70
     checkpoints
    0.66
     stalls
    0.65
     corridors
    0.65
     dams
    0.64
     tunnels
    0.63
     intersections
    0.63
    Activations Density 25.142%

    No Known Activations