© 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. 16446
    Prev
    Next
    INDEX
    Explanations

    words related to physical or abstract limitations or constraints

    oai_token-act-pair · gpt-3.5-turbo

    terms related to illegal or unethical activities and practices

    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
     tops
    -0.62
     Bourbon
    -0.62
     rolled
    -0.60
     Beaver
    -0.59
     brow
    -0.58
     Burns
    -0.57
    ASHINGTON
    -0.57
    anson
    -0.56
     Lol
    -0.56
     shave
    -0.55
    POSITIVE LOGITS
    itably
    1.35
    inately
    1.25
    uably
    1.15
    urities
    1.10
    uable
    1.09
    itable
    1.07
    ivable
    1.06
    icably
    1.06
    ividual
    1.05
    herent
    1.04
    Activations Density 0.044%

    No Known Activations