© 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. 4189
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Char" or variations like "Charlemagne"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Char" followed by various identifiers or descriptors

    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
     Reloaded
    -0.62
    DERR
    -0.62
     delinquent
    -0.60
    æĸ¹
    -0.58
     fielding
    -0.58
     langu
    -0.57
     novel
    -0.57
     cue
    -0.56
     SPD
    -0.56
     harshly
    -0.56
    POSITIVE LOGITS
    coal
    1.36
    itable
    1.34
    itably
    1.34
    isma
    1.20
    acters
    1.19
    izard
    1.08
    ities
    1.03
    cot
    1.01
    ivari
    0.98
    lev
    0.97
    Activations Density 0.032%

    No Known Activations