© 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. 6-RES-JB
    11. 18492
    Prev
    Next
    INDEX
    Explanations

    references to people and position titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arrow
    -0.72
    FIELD
    -0.70
    ties
    -0.70
    thood
    -0.65
     preceded
    -0.63
    amphetamine
    -0.63
    deals
    -0.61
    quit
    -0.61
     depended
    -0.61
     gotta
    -0.60
    POSITIVE LOGITS
     latter
    1.04
     same
    0.98
     interviewer
    0.90
     latest
    0.90
     BBC
    0.83
     audience
    0.81
     aforementioned
    0.80
     agency
    0.80
     nation
    0.80
     extent
    0.78
    Activations Density 0.112%

    No Known Activations