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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-RES-JB
    6. 16874
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ost" or "ost" combined with other characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ost"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Quinn
    -0.68
    ãĥīãĥ©
    -0.68
    ãĥĪ
    -0.67
    kson
    -0.66
     Grayson
    -0.64
    steen
    -0.63
    xon
    -0.63
     Ashes
    -0.61
     slips
    -0.61
    ples
    -0.61
    POSITIVE LOGITS
    algia
    1.33
    rophe
    1.22
    ensibly
    1.19
    rophic
    1.07
    ream
    1.04
    ricting
    1.04
    riction
    1.00
    alg
    0.99
    asis
    0.94
    rand
    0.94
    Activations Density 0.019%

    No Known Activations