© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 4868
    Prev
    Next
    INDEX
    Explanations

    names or words related to "CC" or "CC" with different prefixes

    oai_token-act-pair · gpt-3.5-turbo

    references to "cc" and its variations, likely indicating a focus on carbon copy or content attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lans
    -0.85
    velt
    -0.68
    chest
    -0.66
    cknow
    -0.66
    senal
    -0.65
     Roosevelt
    -0.63
    ĪĴ
    -0.62
     scatter
    -0.61
    staking
    -0.60
    haul
    -0.60
    POSITIVE LOGITS
    entric
    1.16
    aneers
    1.07
    arthy
    1.05
    ombat
    0.98
    anyon
    0.96
    artney
    0.95
    inelli
    0.90
    annon
    0.90
    inct
    0.88
    orpor
    0.88
    Activations Density 0.009%

    No Known Activations