© 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. 8615
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Hook" with varying levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to the Sandy Hook incident and related names or places

    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
    Downloadha
    -0.76
     Paula
    -0.70
    اÙĦ
    -0.65
    Ô
    -0.63
     Scotia
    -0.62
    ICT
    -0.62
    BILITY
    -0.61
     Scient
    -0.60
     solitary
    -0.60
    severe
    -0.59
    POSITIVE LOGITS
     Hook
    1.29
    hook
    1.17
    masters
    0.98
    shot
    0.94
    master
    0.94
    ifax
    0.87
    sett
    0.87
    pipe
    0.86
    Panel
    0.84
    tons
    0.83
    Activations Density 0.007%

    No Known Activations