© 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. 32366
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms

    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
    178
    +0.09
    0.5%
    319
    +0.09
    0.5%
    459
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.09
    0.24
    123
    +0.09
    0.12
    311
    +0.08
    -0.02
    Negative Logits
    ichick
    -0.65
    uyomi
    -0.64
    catentry
    -0.57
     Seym
    -0.57
     Brach
    -0.55
    liga
    -0.55
     Bulg
    -0.53
    llan
    -0.53
    unks
    -0.52
     compr
    -0.52
    POSITIVE LOGITS
    TERN
    1.20
    PUT
    1.13
    CLUD
    1.05
    FORMATION
    1.03
    NER
    0.99
    CLUS
    0.95
    CEPT
    0.94
    strument
    0.94
    STRUCT
    0.92
    FIN
    0.87
    Activations Density 7.799%

    No Known Activations