© 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. 18745
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly the name "Seth"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Seth" in various contexts

    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
    gling
    -0.76
    ilee
    -0.71
    glers
    -0.70
    usterity
    -0.70
    âĶĢâĶĢ
    -0.69
    strap
    -0.67
    ition
    -0.65
    assadors
    -0.65
    Band
    -0.65
    itors
    -0.64
    POSITIVE LOGITS
     Greenberg
    0.77
     Ambro
    0.76
     Pwr
    0.74
     Meh
    0.71
     Conrad
    0.70
    akov
    0.68
     Rollins
    0.68
     Mish
    0.68
    nov
    0.67
    pic
    0.65
    Activations Density 0.070%

    No Known Activations