© 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. 13383
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial independence and standing on one's own feet

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol used in the text

    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
     decom
    -0.70
     Blacks
    -0.67
     Guatem
    -0.67
     convenience
    -0.65
     Garmin
    -0.65
     prostitution
    -0.64
     swast
    -0.62
     Moroccan
    -0.61
     fumble
    -0.61
     Piece
    -0.60
    POSITIVE LOGITS
    ï¸ı
    0.97
    ¯
    0.81
    mand
    0.80
    ulty
    0.79
    ufact
    0.79
    worthiness
    0.79
    ixir
    0.78
    own
    0.77
    tre
    0.77
    âĶĢâĶĢ
    0.76
    Activations Density 0.473%

    No Known Activations