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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4324
    Prev
    Next
    INDEX
    Explanations

    text related to electronic devices and technology companies

    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
    640
    +0.10
    0.5%
    276
    +0.10
    0.5%
    444
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.25
    288
    +0.10
    0.23
    383
    +0.10
    0.12
    Negative Logits
     Nations
    -0.75
     Schools
    -0.67
     Sector
    -0.67
    REDACTED
    -0.66
    hani
    -0.65
     AVG
    -0.65
     Palmer
    -0.64
    DOS
    -0.63
     Universities
    -0.63
     Secondary
    -0.63
    POSITIVE LOGITS
    essage
    1.32
    ming
    1.19
    puter
    1.15
    ortal
    1.14
    orrow
    1.13
    eless
    1.12
    icro
    1.10
    agnetic
    1.09
    isphere
    1.09
    otor
    1.08
    Activations Density 9.683%

    No Known Activations