© 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. 1-RES-JB
    11. 18038
    Prev
    Next
    INDEX
    Explanations

    words related to high-speed impacts or events

    oai_token-act-pair · gpt-3.5-turbo

    words related to ricochet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hunt
    -0.79
    ĪĴ
    -0.75
    mother
    -0.72
    ħĭ
    -0.71
    OVA
    -0.71
    leigh
    -0.68
    knife
    -0.68
    nor
    -0.67
     Woman
    -0.67
    âĦ¢:
    -0.67
    POSITIVE LOGITS
     ric
    1.06
    aution
    0.95
    osion
    0.84
    inel
    0.83
    hess
    0.81
    ision
    0.80
     acid
    0.75
    uci
    0.75
    ipl
    0.73
    asso
    0.72
    Activations Density 0.022%

    No Known Activations