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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 13287
    Prev
    Next
    INDEX
    Explanations

    specific dates or time-related information

    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
    247
    +0.14
    0.6%
    195
    +0.13
    0.5%
    348
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.14
    0.07
    504
    +0.13
    0.06
    325
    +0.13
    0.06
    Negative Logits
    ibilities
    -0.96
    İĭ
    -0.95
    »Ĵ
    -0.92
    vernment
    -0.90
    orpor
    -0.87
    ergic
    -0.81
    anguage
    -0.80
    ensor
    -0.80
    ibles
    -0.79
    essage
    -0.78
    POSITIVE LOGITS
    telling
    1.31
    line
    1.02
     Story
    1.01
     Continued
    0.94
     Transcript
    0.92
    bold
    0.91
    hart
    0.91
    Maker
    0.90
    craft
    0.90
    stal
    0.89
    Activations Density 5.298%

    No Known Activations