© 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. 8-RES-JB
    11. 6508
    Prev
    Next
    INDEX
    Explanations

    words associated with positive feedback or reviews

    oai_token-act-pair · gpt-3.5-turbo

    positive evaluations or testimonials about books

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Words associated with positive feedback or reviews

    Explanation Uploaded by User
    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
    •GPT2 Layer 8 Movie Sentiment Features

    No Comments

    Negative Logits
    coded
    -0.73
    ogenesis
    -0.69
    soDeliveryDate
    -0.68
    onds
    -0.64
     corresponding
    -0.64
    ariat
    -0.64
    ozo
    -0.61
     vow
    -0.61
     reckoning
    -0.60
     contingency
    -0.60
    POSITIVE LOGITS
     Helpful
    1.16
    Excellent
    1.08
     Excellent
    1.00
     excellent
    0.92
    Recommend
    0.91
    cellent
    0.88
     Defin
    0.88
    Overall
    0.87
     Recommend
    0.86
     Highly
    0.86
    Activations Density 0.808%

    No Known Activations