© 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. 31770
    Prev
    Next
    INDEX
    Explanations

    specific entities or companies in the context of business transactions or events

    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
    382
    +0.04
    0.5%
    437
    +0.04
    0.4%
    373
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.04
    0.11
    288
    +0.04
    0.19
    326
    +0.04
    0.19
    Negative Logits
    orius
    -0.32
     bye
    -0.28
    tery
    -0.27
    washer
    -0.27
     Mub
    -0.26
    ifier
    -0.26
     corpus
    -0.26
    cheat
    -0.25
     streak
    -0.24
    codes
    -0.24
    POSITIVE LOGITS
    UTION
    0.41
    ues
    0.36
    VEL
    0.36
    OUGH
    0.34
    ODY
    0.33
    mberg
    0.32
    AND
    0.30
    ocating
    0.30
    OPER
    0.30
    ISTORY
    0.29
    Activations Density 5.836%

    No Known Activations