Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40083
    Prev
    Next
    INDEX
    Explanations

    sequences related to technological specifications or identifiers

    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
    481
    +0.13
    0.5%
    342
    +0.13
    0.5%
    267
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.15
    238
    +0.13
    0.07
    325
    +0.12
    0.07
    Negative Logits
    theless
    -1.09
    ModLoader
    -0.91
    inelli
    -0.90
    pedia
    -0.85
    hare
    -0.82
     corrid
    -0.82
    cellent
    -0.81
    istical
    -0.81
    FontSize
    -0.80
     reconc
    -0.80
    POSITIVE LOGITS
     partName
    1.15
     srfN
    0.93
     EVENTS
    0.80
     <+
    0.80
     attRot
    0.78
     Avg
    0.76
    Jr
    0.76
     Experimental
    0.75
     Zig
    0.74
     Unified
    0.73
    Activations Density 4.757%

    No Known Activations