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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44992
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and social issues

    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
    +0.29
    1.6%
    393
    +0.27
    1.4%
    36
    +0.21
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.29
    0.31
    393
    +0.27
    0.27
    640
    +0.21
    0.27
    Negative Logits
    Edit
    -0.90
    Versions
    -0.70
     edits
    -0.68
    books
    -0.68
    Events
    -0.67
    edit
    -0.66
    sheets
    -0.63
    events
    -0.62
    names
    -0.62
    views
    -0.62
    POSITIVE LOGITS
     reminder
    1.03
     huge
    1.01
     lot
    1.00
     testament
    0.93
     bit
    0.93
     relatively
    0.91
     HUGE
    0.91
     fascinating
    0.90
     constant
    0.90
    versive
    0.90
    Activations Density 12.036%

    No Known Activations