© 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. 16916
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific institution or team, represented by the term "Ole Miss"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity related to sports or academia

    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
    DERR
    -0.83
    ãĤ¢ãĥ«
    -0.81
    olver
    -0.76
    stroke
    -0.74
    adr
    -0.73
    icted
    -0.73
    ies
    -0.70
    iles
    -0.69
    oys
    -0.68
    plain
    -0.67
    POSITIVE LOGITS
    tto
    0.94
    lla
    0.89
    mic
    0.82
    tti
    0.81
    lli
    0.80
    cular
    0.80
    cules
    0.77
    avement
    0.75
    utenant
    0.75
    chnology
    0.75
    Activations Density 0.051%

    No Known Activations