© 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. 14832
    Prev
    Next
    INDEX
    Explanations

    mentions of unidentified or unnamed entities in reports or statements

    oai_token-act-pair · gpt-3.5-turbo

    references to unnamed or unidentified individuals and sources

    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
    ometers
    -0.80
    byss
    -0.79
    arium
    -0.76
    ebook
    -0.75
    efficient
    -0.71
    parser
    -0.71
    hes
    -0.69
    Interstitial
    -0.67
    nea
    -0.67
    Dialog
    -0.66
    POSITIVE LOGITS
     unnamed
    0.94
     unspecified
    0.84
     persons
    0.75
     unidentified
    0.75
    aneous
    0.73
    worldly
    0.72
     undisclosed
    0.72
     narrator
    0.66
     quantity
    0.64
     sourcing
    0.64
    Activations Density 0.035%

    No Known Activations