© 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. 1-RES-JB
    11. 3164
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jackie"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jackie."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    byter
    -0.90
    places
    -0.80
    taboola
    -0.77
    icult
    -0.75
    agn
    -0.71
    pmwiki
    -0.71
    umbn
    -0.70
    sense
    -0.70
    merce
    -0.69
    ictions
    -0.68
    POSITIVE LOGITS
     Jackie
    1.23
     Chun
    0.84
     Kennedy
    0.82
     Mew
    0.81
     Polo
    0.77
     Chan
    0.75
     Rica
    0.74
     clen
    0.73
     Stones
    0.73
     Nak
    0.71
    Activations Density 0.011%

    No Known Activations