© 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. 7051
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and variations of the word "perform" in various contexts

    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
    inki
    -0.71
    izons
    -0.69
    ipedia
    -0.69
    rack
    -0.69
    unity
    -0.69
    issue
    -0.68
    ener
    -0.66
    Nusra
    -0.65
    edia
    -0.63
    ourcing
    -0.63
    POSITIVE LOGITS
     miracles
    1.17
     tasks
    1.12
     duties
    1.11
     stunts
    1.08
     feats
    1.07
     abortions
    0.99
     surgeries
    0.97
     rituals
    0.97
     tricks
    0.96
     chores
    0.96
    Activations Density 0.125%

    No Known Activations