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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 40176
    Prev
    Next
    INDEX
    Explanations

    polling data and statistics related to political races and candidates

    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
    745
    +0.09
    0.5%
    447
    +0.08
    0.5%
    342
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    577
    +0.09
    0.09
    607
    +0.08
    0.07
    517
    +0.08
    0.08
    Negative Logits
    ĨĴ
    -0.57
    abi
    -0.55
     essentials
    -0.54
     Agric
    -0.53
     garg
    -0.52
     sacrific
    -0.52
     icing
    -0.50
     stockp
    -0.49
    din
    -0.49
    RIP
    -0.48
    POSITIVE LOGITS
    lash
    0.66
    Downloadha
    0.61
     underestimate
    0.61
     Eag
    0.59
    eele
    0.58
     margin
    0.57
     (+
    0.57
     til
    0.55
     underest
    0.54
     favoring
    0.53
    Activations Density 9.675%

    No Known Activations