© 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. 32454
    Prev
    Next
    INDEX
    Explanations

    fractions related to quantities or proportions

    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
    +0.11
    0.6%
    166
    +0.10
    0.5%
    195
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.18
    9
    +0.10
    0.14
    497
    +0.09
    0.17
    Negative Logits
    league
    -0.71
    values
    -0.64
    ordes
    -0.59
    verbs
    -0.58
    anca
    -0.58
    cru
    -0.56
    beh
    -0.56
    Trend
    -0.55
     semin
    -0.55
     pastoral
    -0.55
    POSITIVE LOGITS
    ï¸ı
    0.70
    icago
    0.66
    imet
    0.64
    姫
    0.63
    ority
    0.60
     thereof
    0.60
    irty
    0.60
    enary
    0.59
     percent
    0.59
     ABV
    0.59
    Activations Density 14.726%

    No Known Activations