© 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. 16432
    Prev
    Next
    INDEX
    Explanations

    terms related to file extensions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ext"

    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
    externalActionCode
    -0.84
    manship
    -0.78
    ItemImage
    -0.77
    hari
    -0.76
    ker
    -0.76
    ghai
    -0.76
    Reviewer
    -0.74
    Downloadha
    -0.73
    folk
    -0.71
    Cola
    -0.65
    POSITIVE LOGITS
    ensions
    1.36
    ension
    1.27
    ract
    1.23
    racted
    1.23
    inct
    1.22
    ended
    1.11
    ortion
    1.01
    ENDED
    0.99
    ractor
    0.97
    raction
    0.93
    Activations Density 0.006%

    No Known Activations