© 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. 10-RES-JB
    11. 14055
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    oai_token-act-pair · gpt-3.5-turbo

    ordinal numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    infeld
    -0.75
    bos
    -0.65
    enne
    -0.64
    cks
    -0.64
    Cra
    -0.63
     Chow
    -0.63
    roth
    -0.62
    IDA
    -0.62
    info
    -0.61
    inen
    -0.61
    POSITIVE LOGITS
    ousand
    1.15
     inning
    1.13
    teenth
    1.08
    irty
    1.07
     percentile
    0.98
    ousands
    0.97
     century
    0.95
     amendment
    0.94
     Amendment
    0.91
    ieth
    0.89
    Activations Density 0.049%

    No Known Activations