© 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. 6-RES-JB
    11. 18866
    Prev
    Next
    INDEX
    Explanations

    words related to incidents, events, and equipment used in organized activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of significant events or items related to conflict, challenges, and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.55
    rique
    -0.52
    EVA
    -0.51
    Delivery
    -0.49
    LESS
    -0.48
    scape
    -0.46
    Ł
    -0.44
    Care
    -0.44
     Condition
    -0.43
     Thing
    -0.43
    POSITIVE LOGITS
    mith
    1.03
    heet
    0.96
    creen
    0.96
    pring
    0.93
    chool
    0.93
    hooting
    0.92
    uggest
    0.91
    poons
    0.90
    paces
    0.90
    ourcing
    0.89
    Activations Density 0.987%

    No Known Activations