© 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. 10-RES-JB
    11. 11394
    Prev
    Next
    INDEX
    Explanations

    positive or negative evaluative words

    oai_token-act-pair · gpt-3.5-turbo

    positive and negative evaluations or judgments about situations

    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
    aneers
    -0.76
    ngth
    -0.76
    arij
    -0.76
    ividual
    -0.71
    assemb
    -0.69
    iries
    -0.68
    velop
    -0.67
    rive
    -0.67
    mop
    -0.65
    icipated
    -0.64
    POSITIVE LOGITS
     considering
    1.09
     because
    0.95
     ðŁĻĤ
    0.79
    !
    0.79
     eh
    0.78
     reasoning
    0.77
    soType
    0.75
     news
    0.75
    because
    0.75
     advice
    0.74
    Activations Density 0.160%

    No Known Activations