© 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. 7-RES-JB
    11. 10030
    Prev
    Next
    INDEX
    Explanations

    the phrase "a little"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of small quantities or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eneg
    -0.82
    osponsors
    -0.81
    orthy
    -0.78
    atars
    -0.75
    yrim
    -0.75
    ourses
    -0.74
    atu
    -0.73
    antage
    -0.73
    ullivan
    -0.72
    istar
    -0.72
    POSITIVE LOGITS
     bit
    1.45
     BIT
    0.88
     extra
    0.81
     peek
    0.81
     girl
    0.81
     glimpse
    0.79
     patience
    0.77
     Bit
    0.75
     tad
    0.73
     chunk
    0.73
    Activations Density 0.034%

    No Known Activations