© 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. 32240
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer hardware and software components

    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
    648
    +0.02
    0.5%
    88
    +0.02
    0.5%
    44
    +0.01
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.02
    0.61
    640
    +0.02
    0.56
    375
    +0.01
    0.07
    Negative Logits
    nces
    -0.12
    itatively
    -0.12
    cens
    -0.12
     eleph
    -0.11
    itiveness
    -0.11
    andowski
    -0.10
    stanbul
    -0.10
    naire
    -0.10
     multiplied
    -0.10
    izont
    -0.10
    POSITIVE LOGITS
     toast
    0.12
    zac
    0.12
     cir
    0.12
    anie
    0.11
     emergencies
    0.11
     srfAttach
    0.11
    Marie
    0.10
    ck
    0.10
    otle
    0.10
    ciation
    0.10
    Activations Density 39.152%

    No Known Activations