© 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. 3-RES-JB
    11. 14728
    Prev
    Next
    INDEX
    Explanations

    people's names, particularly the name "Dylan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Dylan" and related figures or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rontal
    -0.84
     actionGroup
    -0.83
    spr
    -0.71
    llah
    -0.70
     satell
    -0.69
    ments
    -0.65
     WATCHED
    -0.65
    Magikarp
    -0.63
     extremes
    -0.62
    MENT
    -0.60
    POSITIVE LOGITS
     Dylan
    1.00
    rolet
    0.87
     TAMADRA
    0.83
    hedral
    0.83
    seys
    0.82
    elta
    0.79
     Moran
    0.78
    ylan
    0.78
     Matthews
    0.75
     CLS
    0.72
    Activations Density 0.009%

    No Known Activations