© 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. 11244
    Prev
    Next
    INDEX
    Explanations

    numbers in the range of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number 44 in different contexts

    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
    glers
    -0.73
    perm
    -0.72
     Ou
    -0.66
     denomin
    -0.65
    bos
    -0.63
     Hels
    -0.63
    reek
    -0.61
    ality
    -0.61
    reb
    -0.61
     foss
    -0.59
    POSITIVE LOGITS
    00
    0.97
    44
    0.95
    393
    0.90
    68
    0.88
    APH
    0.85
    CHAT
    0.84
    73
    0.84
    455
    0.83
    45
    0.83
    74
    0.82
    Activations Density 0.017%

    No Known Activations