© 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. 6-RES-JB
    11. 1656
    Prev
    Next
    INDEX
    Explanations

    mentions of the acronym "ASA"

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific punctuation mark or end-of-text character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sburgh
    -0.91
    rigan
    -0.82
    ding
    -0.82
    ships
    -0.81
    raising
    -0.77
    tted
    -0.74
    auld
    -0.73
    tor
    -0.71
    ingham
    -0.71
    wig
    -0.70
    POSITIVE LOGITS
    conservancy
    0.89
     Species
    0.86
    ñ
    0.86
    BILITIES
    0.76
    qua
    0.75
    quez
    0.75
    llan
    0.75
    pling
    0.75
     eru
    0.72
    ño
    0.71
    Activations Density 0.065%

    No Known Activations