© 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. 11-RES-JB
    11. 22674
    Prev
    Next
    INDEX
    Explanations

    individuals with specific characteristics or backgrounds

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personal history and credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olin
    -0.68
    pload
    -0.61
    aea
    -0.60
    Ground
    -0.59
     cradle
    -0.58
    izont
    -0.58
     Mex
    -0.57
    uesday
    -0.57
    ONSORED
    -0.56
    updated
    -0.55
    POSITIVE LOGITS
     who
    1.01
     whom
    0.95
    who
    0.95
     backgrounds
    0.89
     chops
    0.86
     stature
    0.82
     fame
    0.80
     penchant
    0.79
     capable
    0.79
     flair
    0.78
    Activations Density 0.283%

    No Known Activations