© 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 EvalsExportsAPI 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. 33226
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal investigations and incidents

    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
    +0.35
    1.9%
    441
    +0.10
    0.5%
    679
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.35
    0.25
    142
    +0.10
    0.13
    561
    +0.09
    0.11
    Negative Logits
    ï¸
    -0.73
    WithNo
    -0.67
     Himself
    -0.64
    izont
    -0.61
    Translation
    -0.60
    Interstitial
    -0.60
    Justice
    -0.59
    Occup
    -0.59
    à¦
    -0.58
    regn
    -0.58
    POSITIVE LOGITS
     goodbye
    0.77
    doms
    0.66
     troopers
    0.60
     they
    0.60
     investigators
    0.59
     warranties
    0.55
     tentative
    0.54
     Hancock
    0.52
     preliminary
    0.52
     delays
    0.52
    Activations Density 11.953%

    No Known Activations