© 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. 11-RES-JB
    11. 22618
    Prev
    Next
    INDEX
    Explanations

    details about being the first or achieving a significant milestone in a particular field

    oai_token-act-pair · gpt-3.5-turbo

    references to first achievements or milestones across various categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¦ãĤ¹
    -0.62
    ggles
    -0.61
    utterstock
    -0.59
    isites
    -0.59
    asty
    -0.59
    may
    -0.59
     Secrets
    -0.58
    ruciating
    -0.57
    cffff
    -0.57
    apters
    -0.57
    POSITIVE LOGITS
     ever
    1.17
     to
    1.04
     EVER
    0.97
     since
    0.90
    ever
    0.84
     besides
    0.79
    to
    0.78
     born
    0.77
     prosecuted
    0.76
     diagnosed
    0.74
    Activations Density 0.159%

    No Known Activations