© 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. 14325
    Prev
    Next
    INDEX
    Explanations

    sequences and mentions related to counting

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to counting and amounts

    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
    avage
    -0.79
    rouse
    -0.75
    Policy
    -0.71
    amily
    -0.70
    nered
    -0.69
    hement
    -0.68
    owered
    -0.67
    facing
    -0.67
     habitat
    -0.66
     backdrop
    -0.65
    POSITIVE LOGITS
     tally
    0.99
     elapsed
    0.98
     casualties
    0.97
     calories
    0.97
     accomplishments
    0.96
     totals
    0.95
     digits
    0.95
     successes
    0.94
     victories
    0.92
     blessings
    0.91
    Activations Density 0.226%

    No Known Activations