© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 23772
    Prev
    Next
    INDEX
    Explanations

    actions or behaviors related to interactions or conflicts between people

    oai_token-act-pair · gpt-3.5-turbo

    statements of being or actions that indicate assertiveness or confrontation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boards
    -0.80
    iann
    -0.75
    Keys
    -0.72
    assadors
    -0.68
    ributes
    -0.68
    uesday
    -0.66
    imon
    -0.66
     afterward
    -0.65
    inth
    -0.65
     thereafter
    -0.65
    POSITIVE LOGITS
     misunderstood
    1.04
     wrong
    1.01
     Wrong
    0.99
     underest
    0.89
     miscon
    0.85
     mistaken
    0.85
     misunderstanding
    0.83
     correctly
    0.81
     exagger
    0.80
     unwittingly
    0.80
    Activations Density 0.593%

    No Known Activations