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. 4271
    Prev
    Next
    INDEX
    Explanations

    information related to financial frugality and budgeting

    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
    616
    +0.08
    0.5%
    128
    +0.08
    0.5%
    146
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.08
    0.03
    326
    +0.08
    0.23
    616
    +0.07
    0.07
    Negative Logits
     Dresden
    -0.48
     Gutenberg
    -0.47
     Dunham
    -0.47
    prints
    -0.46
     pronounced
    -0.46
     Sparkle
    -0.45
    ISO
    -0.44
    hower
    -0.42
     Mississ
    -0.42
    eting
    -0.42
    POSITIVE LOGITS
    uay
    0.70
    rug
    0.69
    osity
    0.68
    ulus
    0.66
    ulent
    0.63
    atism
    0.63
    ular
    0.60
    ula
    0.59
    roup
    0.58
    ulence
    0.58
    Activations Density 9.555%

    No Known Activations