Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10287
    Prev
    Next
    INDEX
    Explanations

    text in a different script or language, potentially with a specific character set and format

    oai_token-act-pair · gpt-3.5-turbo

    sequences related to non-English characters or symbols

    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
    arya
    -0.75
    bitious
    -0.74
    Downloadha
    -0.74
    cliffe
    -0.74
    conn
    -0.69
    erto
    -0.67
    hani
    -0.67
     zoning
    -0.67
    STD
    -0.65
     loophole
    -0.64
    POSITIVE LOGITS
    ©¶æ
    0.72
    Mobile
    0.72
    ographic
    0.70
     Legends
    0.69
    å§
    0.66
    etheless
    0.66
    ursday
    0.66
    rencies
    0.64
     Pell
    0.64
    ÏĤ
    0.63
    Activations Density 0.329%

    No Known Activations