© 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. 18686
    Prev
    Next
    INDEX
    Explanations

    pronouns and modal verbs indicating possibilities or actions

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and references to collective actions 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
    bats
    -0.66
    xit
    -0.64
    hend
    -0.62
    oner
    -0.59
    oling
    -0.58
    oward
    -0.57
     honorable
    -0.57
    idge
    -0.57
    prising
    -0.56
     Whatever
    -0.56
    POSITIVE LOGITS
     already
    1.12
     rarely
    1.08
     seldom
    0.99
     hadn
    0.98
     lacks
    0.95
     tends
    0.93
     cannot
    0.93
     hasn
    0.92
     never
    0.91
     lacked
    0.91
    Activations Density 0.467%

    No Known Activations