© 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. 4815
    Prev
    Next
    INDEX
    Explanations

    fractions like "one-third" in text data

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical fractions or proportions

    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
     tremend
    -0.78
     reg
    -0.68
     combust
    -0.66
     deduct
    -0.64
    auna
    -0.63
     corrid
    -0.61
     key
    -0.60
     eleph
    -0.60
     booming
    -0.59
     unpredictable
    -0.59
    POSITIVE LOGITS
    tenance
    1.20
    theless
    1.05
    lihood
    1.02
    terday
    0.97
    igham
    0.86
    iscopal
    0.85
    !--
    0.83
    tesy
    0.82
    Rus
    0.80
    mosp
    0.78
    Activations Density 0.026%

    No Known Activations