© 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. 17967
    Prev
    Next
    INDEX
    Explanations

    specific sequences of Roman numerals

    oai_token-act-pair · gpt-3.5-turbo

    the Roman numeral 'II'

    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
    =-=-=-=-=-=-=-=-
    -0.74
    ãĥ¼ãĥĨ
    -0.71
    ãĥ£
    -0.70
    manager
    -0.69
    reens
    -0.68
    acters
    -0.66
    */(
    -0.65
    ãĤ±
    -0.65
     multiplier
    -0.65
    ":["
    -0.64
    POSITIVE LOGITS
    III
    1.16
    II
    1.14
     III
    0.88
     Britann
    0.85
     II
    0.84
    FY
    0.84
    HF
    0.77
    igon
    0.74
    ATA
    0.73
    agna
    0.70
    Activations Density 0.011%

    No Known Activations