© 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. 10-RES-JB
    11. 17355
    Prev
    Next
    INDEX
    Explanations

    the possessive form of words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's' in various contexts

    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
     Nero
    -0.69
     horses
    -0.61
     stressed
    -0.61
    è£ħ
    -0.61
     fret
    -0.60
     referrals
    -0.60
     Spart
    -0.59
     Rothschild
    -0.58
     Ping
    -0.57
    Bey
    -0.57
    POSITIVE LOGITS
    atisf
    1.52
    aturated
    1.45
    olutions
    1.42
    atellite
    1.41
    ourced
    1.41
    ources
    1.41
    olution
    1.41
    ixty
    1.38
    ensitivity
    1.38
    pecially
    1.38
    Activations Density 0.056%

    No Known Activations