© 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. 8-RES-JB
    11. 18456
    Prev
    Next
    INDEX
    Explanations

    queries that start with phrases like "Did you know" or "Do you think"

    oai_token-act-pair · gpt-3.5-turbo

    questions or statements that involve knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yssey
    -0.76
    enez
    -0.73
    imil
    -0.72
    inis
    -0.72
    Ide
    -0.68
    ensibly
    -0.67
    abba
    -0.66
    inki
    -0.65
    atha
    -0.65
    erenn
    -0.65
    POSITIVE LOGITS
    ...?
    1.26
    ?"
    1.23
    ?
    1.21
    ?'
    1.19
    ?:
    1.18
    ?".
    1.17
    ?!
    1.16
    ?'"
    1.14
    ?!"
    1.12
    ?",
    1.10
    Activations Density 0.113%

    No Known Activations