© 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. 7-RES-JB
    11. 13360
    Prev
    Next
    INDEX
    Explanations

    phrases related to boards, like "headboard" and "switchboard"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "board" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENC
    -0.76
    uality
    -0.74
     Mes
    -0.66
    pert
    -0.65
     Caesar
    -0.64
     Lerner
    -0.64
    onso
    -0.62
     Walton
    -0.62
     pand
    -0.62
     Dynamo
    -0.62
    POSITIVE LOGITS
    board
    1.13
     layouts
    1.02
    tops
    0.92
     Layout
    0.92
     layout
    0.91
    walk
    0.89
    boards
    0.87
    lists
    0.82
    boarding
    0.82
    */(
    0.81
    Activations Density 0.022%

    No Known Activations