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

    Neuronpedia

    Jacobian LensNEW
    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. 3424
    Prev
    Next
    INDEX
    Explanations

    instances of decision-making and choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases about making choices or decisions

    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
    metadata
    -0.79
    rote
    -0.69
    scope
    -0.68
    rites
    -0.67
    meta
    -0.67
    bound
    -0.66
    estones
    -0.66
    visible
    -0.66
     workings
    -0.65
    hooting
    -0.65
    POSITIVE LOGITS
     either
    0.97
    Either
    0.93
     Either
    0.92
    either
    0.86
    Option
    0.78
     whichever
    0.78
     option
    0.75
     choose
    0.73
     chose
    0.73
     Carbuncle
    0.72
    Activations Density 0.370%

    No Known Activations