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. 33567
    Prev
    Next
    INDEX
    Explanations

    measurements of volume or quantity

    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
    16
    +0.13
    0.5%
    566
    +0.13
    0.5%
    553
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    595
    +0.13
    0.08
    159
    +0.13
    0.09
    48
    +0.12
    0.09
    Negative Logits
    xus
    -0.90
    Downloadha
    -0.87
    CVE
    -0.78
    DonaldTrump
    -0.77
     Decay
    -0.75
    hler
    -0.74
    088
    -0.74
    ä½ľ
    -0.73
    FactoryReloaded
    -0.73
    sonian
    -0.73
    POSITIVE LOGITS
    igated
    1.28
    ters
    1.25
    urgy
    1.25
    igating
    1.19
    igators
    1.19
    urgical
    1.17
    lit
    1.14
    igious
    1.11
    igation
    1.11
    eral
    1.09
    Activations Density 7.017%

    No Known Activations