© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 1237
    Prev
    Next
    INDEX
    Explanations

    modal verbs such as "can," "could," "may," "might," "will," and "must" along with opinions and assertions

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases regarding possibility or permission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     culminating
    -0.64
    assi
    -0.62
    conom
    -0.57
    RFC
    -0.56
     dilig
    -0.55
     culminated
    -0.55
    rahim
    -0.52
     Cortex
    -0.52
    ipes
    -0.52
    ngth
    -0.52
    POSITIVE LOGITS
     not
    1.59
    not
    1.53
     never
    1.42
     NOT
    1.37
    Not
    1.36
     Not
    1.32
    't
    1.30
     doesn
    1.29
     didn
    1.27
     hasn
    1.27
    Activations Density 1.662%

    No Known Activations