© 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. 7-RES-JB
    11. 17183
    Prev
    Next
    INDEX
    Explanations

    mentions of AI

    oai_token-act-pair · gpt-3.5-turbo

    references to artificial intelligence (AI)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.92
     Townsend
    -0.77
    ados
    -0.72
    cake
    -0.72
    ibel
    -0.69
    ings
    -0.67
    adoes
    -0.66
     Rack
    -0.66
     Wem
    -0.65
    atin
    -0.65
    POSITIVE LOGITS
    onomous
    0.73
    OC
    0.71
    HA
    0.70
    BI
    0.70
    Bs
    0.70
    atson
    0.69
    GR
    0.68
    GEN
    0.67
    FP
    0.65
     theoret
    0.64
    Activations Density 0.013%

    No Known Activations