© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11658
    Prev
    Next
    INDEX
    Explanations

    words related to revealing or uncovering something

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "curtain" in various contexts

    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
    liness
    -0.73
    board
    -0.72
    STEM
    -0.68
    DragonMagazine
    -0.68
    usterity
    -0.68
    ebook
    -0.67
    \\\\\\\\
    -0.67
    lime
    -0.63
    tu
    -0.63
    boarding
    -0.62
    POSITIVE LOGITS
    glers
    0.99
    orset
    0.73
    anyon
    0.73
    orship
    0.72
    berra
    0.72
    ulkan
    0.69
    oenix
    0.67
     Speedway
    0.67
    wark
    0.67
    ão
    0.66
    Activations Density 0.084%

    No Known Activations