© 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. 8-RES-JB
    11. 22502
    Prev
    Next
    INDEX
    Explanations

    mentions of academic professionals or professors

    oai_token-act-pair · gpt-3.5-turbo

    references to academic professionals, specifically professors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     territ
    -0.66
     Bundy
    -0.65
     launchers
    -0.64
     deployment
    -0.64
    tera
    -0.64
    opter
    -0.63
     Pradesh
    -0.63
     Devils
    -0.61
     leash
    -0.60
     Clan
    -0.60
    POSITIVE LOGITS
    essors
    1.24
     emer
    1.19
    iate
    1.04
    itatively
    1.00
    essor
    0.99
    ials
    0.95
     specializing
    0.92
    hips
    0.90
    onym
    0.90
    ertation
    0.89
    Activations Density 0.031%

    No Known Activations