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. 13403
    Prev
    Next
    INDEX
    Explanations

    social media-related terms and discussions

    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
    288
    +0.19
    0.9%
    447
    +0.19
    0.9%
    508
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    508
    +0.19
    0.07
    132
    +0.19
    0.05
    381
    +0.12
    0.06
    Negative Logits
    nces
    -0.96
    xual
    -0.94
    ilts
    -0.84
    atche
    -0.76
     Centauri
    -0.72
    ecause
    -0.72
    manuel
    -0.71
     Flore
    -0.70
    shall
    -0.69
    ç·
    -0.69
    POSITIVE LOGITS
     networks
    0.90
     networking
    0.89
    izing
    0.83
    istic
    0.77
    ized
    0.76
     cues
    0.75
     influ
    0.75
     interaction
    0.73
     network
    0.73
     interactions
    0.72
    Activations Density 6.291%

    No Known Activations