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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1180
    Prev
    Next
    INDEX
    Explanations

    words related to invisibility or completion

    oai_token-act-pair · gpt-3.5-turbo

    words related to visibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ante
    -0.75
    iddle
    -0.70
    ingham
    -0.63
     tong
    -0.62
    aito
    -0.61
    agu
    -0.61
     Alleg
    -0.61
    eng
    -0.60
     bandwagon
    -0.60
     Aj
    -0.60
    POSITIVE LOGITS
    visible
    1.23
    isible
    0.78
    itate
    0.72
     Liter
    0.72
    leness
    0.68
     exported
    0.68
    represented
    0.65
     Universities
    0.65
     Dise
    0.63
    ufact
    0.62
    Activations Density 0.000%

    No Known Activations