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

    Neuronpedia

    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. 4715
    Prev
    Next
    INDEX
    Explanations

    words related to technology and potential security threats

    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
    393
    +0.14
    0.5%
    718
    +0.13
    0.5%
    253
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.20
    703
    +0.13
    0.08
    384
    +0.11
    0.06
    Negative Logits
    aim
    -1.07
    rend
    -0.98
    idelines
    -0.88
    ffen
    -0.86
    othy
    -0.85
    IGHT
    -0.84
    ync
    -0.83
    emp
    -0.82
    ired
    -0.81
    isen
    -0.81
    POSITIVE LOGITS
     remotely
    1.15
     tho
    0.90
    romeda
    0.87
     though
    0.85
     moderately
    0.83
     outright
    0.83
    monary
    0.81
     stranger
    0.79
    handedly
    0.79
     sshd
    0.75
    Activations Density 6.830%

    No Known Activations