© 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. 9-RES-JB
    11. 6945
    Prev
    Next
    INDEX
    Explanations

    the concept of judgment or evaluation regarding decisions or choices

    oai_token-act-pair · gpt-3.5-turbo

    expressions of value judgments related to ideas or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -1.00
    ĸļ
    -0.77
    cart
    -0.70
    racuse
    -0.68
    uckle
    -0.67
    cled
    -0.66
    lov
    -0.65
    ategory
    -0.65
    ngth
    -0.65
    stals
    -0.65
    POSITIVE LOGITS
     thing
    0.92
     predictor
    0.92
     incentive
    0.89
     idea
    0.89
     indicator
    0.88
     deterrent
    0.85
     indication
    0.78
     incentives
    0.77
     sign
    0.77
     motiv
    0.76
    Activations Density 0.149%

    No Known Activations