© 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. 4-RES-JB
    11. 10303
    Prev
    Next
    INDEX
    Explanations

    names related to "Dolan."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Dolan" in relation to a specific individual

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

    No Comments

    Negative Logits
    IRED
    -0.74
    trak
    -0.69
    ired
    -0.69
    ERAL
    -0.67
     repeat
    -0.67
    olk
    -0.65
     WATCHED
    -0.65
    req
    -0.63
     Nemesis
    -0.62
    rising
    -0.62
    POSITIVE LOGITS
     Heights
    1.02
    olan
    1.00
    osaurs
    0.79
    osaurus
    0.78
    zees
    0.77
    ese
    0.76
    vre
    0.76
    lein
    0.75
    unci
    0.74
    oad
    0.72
    Activations Density 0.014%

    No Known Activations