© 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. 20439
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs, indicating expressions of emotion and behavior

    oai_token-act-pair · gpt-3.5-turbo

    contractions and forms of the verb "to be."

    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
    icipated
    -0.77
    sequently
    -0.76
    sequent
    -0.70
    inges
    -0.70
     redes
    -0.69
    edIn
    -0.68
     Additionally
    -0.67
    pmwiki
    -0.67
    inav
    -0.66
     undertook
    -0.66
    POSITIVE LOGITS
     gonna
    1.46
     gotta
    1.15
     kidding
    1.15
     fucked
    1.09
     fuckin
    1.05
     fucking
    1.05
     sorry
    1.05
     disgusting
    1.04
     stupid
    1.02
     pathetic
    1.01
    Activations Density 0.227%

    No Known Activations