© 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. 9-RES-JB
    11. 4701
    Prev
    Next
    INDEX
    Explanations

    phrases related to location, actions, and occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to political or social dominance and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vier
    -0.72
    oops
    -0.60
    ueless
    -0.60
     obscurity
    -0.58
     JUST
    -0.58
    ¥µ
    -0.58
    anyahu
    -0.57
    ookie
    -0.57
    ommel
    -0.55
     Ending
    -0.54
    POSITIVE LOGITS
    .[
    0.82
     thereto
    0.82
    soever
    0.79
    .","
    0.76
    ;
    0.76
    .
    0.75
    .''.
    0.74
     therein
    0.74
     interact
    0.72
     interacts
    0.72
    Activations Density 0.771%

    No Known Activations