© 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. 34905
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons, purposes, or justifications

    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
    +0.19
    0.9%
    326
    +0.12
    0.6%
    327
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    635
    +0.19
    0.09
    362
    +0.12
    0.10
    86
    +0.12
    0.06
    Negative Logits
    allic
    -0.65
    ibr
    -0.65
     corrid
    -0.63
     Fired
    -0.61
     helicop
    -0.59
     monop
    -0.58
    alien
    -0.57
     bombshell
    -0.56
    NetMessage
    -0.56
    ombs
    -0.56
    POSITIVE LOGITS
     sake
    0.89
    peria
    0.84
    rior
    0.82
    lihood
    0.82
    resy
    0.79
    rifice
    0.77
    olicy
    0.76
    )].
    0.75
    urities
    0.71
    edIn
    0.71
    Activations Density 9.808%

    No Known Activations