© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11308
    Prev
    Next
    INDEX
    Explanations

    academics and professionals associated with universities or research institutions

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles related to academic and professional expertise

    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
     idiots
    -0.87
    ombies
    -0.74
    rums
    -0.73
     Blacks
    -0.73
    ouls
    -0.73
     Parties
    -0.73
     chests
    -0.73
     needles
    -0.71
    Ts
    -0.71
     puppies
    -0.70
    POSITIVE LOGITS
     specializing
    0.87
    hunter
    0.86
    alyst
    0.80
    pillar
    0.77
    etter
    0.77
     spokesperson
    0.75
    abase
    0.74
     assistant
    0.73
     planner
    0.72
    rower
    0.71
    Activations Density 0.135%

    No Known Activations