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. 34670
    Prev
    Next
    INDEX
    Explanations

    information related to financial transactions, economic reforms, and political statements

    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
    487
    +0.09
    0.5%
    68
    +0.09
    0.5%
    618
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.09
    0.16
    159
    +0.09
    0.13
    393
    +0.08
    0.25
    Negative Logits
    kamp
    -0.59
     SHOULD
    -0.56
    PATH
    -0.55
    Universal
    -0.51
     Pulse
    -0.51
    wave
    -0.50
     GENERAL
    -0.49
     Croatian
    -0.49
     Universal
    -0.49
     SPORTS
    -0.49
    POSITIVE LOGITS
    endum
    0.91
    ressing
    0.87
    ictions
    0.84
    icted
    0.82
    adding
    0.82
    itives
    0.78
    ition
    0.78
    resses
    0.75
    icts
    0.74
    itive
    0.71
    Activations Density 10.078%

    No Known Activations