© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 3775
    Prev
    Next
    INDEX
    Explanations

    names of individuals or characters involved in various incidents 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
    36
    +0.10
    0.5%
    367
    +0.10
    0.5%
    378
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    367
    +0.10
    0.13
    232
    +0.10
    0.09
    326
    +0.08
    0.19
    Negative Logits
    raq
    -0.75
    othal
    -0.75
    mates
    -0.72
    marked
    -0.67
    buck
    -0.66
    teen
    -0.64
    ramid
    -0.64
    fare
    -0.63
    netflix
    -0.63
    handed
    -0.63
    POSITIVE LOGITS
     Martinez
    0.91
     Gomez
    0.82
     Garcia
    0.81
     Gutierrez
    0.80
     Rodriguez
    0.79
     Perez
    0.77
     Fernandez
    0.77
     Rico
    0.77
     Santana
    0.76
     Santos
    0.76
    Activations Density 7.164%

    No Known Activations