© 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. 9099
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "many" in close proximity to other words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "many" and phrases indicating abundance or excess

    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
    ħĭ
    -0.76
    afort
    -0.73
    notation
    -0.71
    owder
    -0.70
    avior
    -0.70
    ername
    -0.69
    morning
    -0.67
    ain
    -0.66
    ivism
    -0.66
    pper
    -0.66
    POSITIVE LOGITS
     times
    1.04
     calories
    1.01
     unanswered
    0.99
     opportunities
    0.99
     variables
    0.95
     entries
    0.95
     facets
    0.93
     hurdles
    0.92
     copies
    0.92
     digits
    0.92
    Activations Density 0.096%

    No Known Activations