© 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. 10-RES-JB
    11. 16415
    Prev
    Next
    INDEX
    Explanations

    locations specified with distances

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     privilege
    -0.73
     Sinai
    -0.70
     privileges
    -0.66
     entitlement
    -0.66
     inaction
    -0.66
     trump
    -0.65
     sage
    -0.64
     privileged
    -0.63
     Baal
    -0.63
     Nost
    -0.63
    POSITIVE LOGITS
    approximately
    1.10
    yards
    1.04
    rough
    0.99
    partial
    0.98
    almost
    0.98
    enough
    0.95
    about
    0.94
    six
    0.93
    ±
    0.92
    mostly
    0.91
    Activations Density 0.037%

    No Known Activations