© 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. 9872
    Prev
    Next
    INDEX
    Explanations

    names or references to people named Ben

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ben" and its variations 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
    oslav
    -0.59
     corners
    -0.57
    lessly
    -0.56
    FORMATION
    -0.55
     foregoing
    -0.55
     ratt
    -0.55
    channelAvailability
    -0.54
     diaper
    -0.54
     sled
    -0.52
     resid
    -0.52
    POSITIVE LOGITS
    amina
    0.76
    urion
    0.75
    anke
    0.73
    hement
    0.71
    amins
    0.70
    asar
    0.70
    iful
    0.67
    ealous
    0.65
    onson
    0.64
    iazep
    0.64
    Activations Density 0.095%

    No Known Activations