© 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. 11-RES-JB
    11. 18694
    Prev
    Next
    INDEX
    Explanations

    quantifiers suggesting high intensity or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating high-quality or desirable attributes related to products or experiences

    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
    anism
    -0.72
    ews
    -0.70
    uploads
    -0.69
    \<
    -0.68
    atell
    -0.65
    ipedia
    -0.64
    AIDS
    -0.64
    bis
    -0.64
    Corp
    -0.61
    due
    -0.61
    POSITIVE LOGITS
     fantastic
    1.29
     terrific
    1.25
     definite
    1.24
     wonderful
    1.22
     great
    1.21
     nice
    1.18
     delightful
    1.16
     lovely
    1.15
     perfect
    1.13
     wonderfully
    1.12
    Activations Density 0.237%

    No Known Activations