© 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. 9-RES-JB
    11. 21191
    Prev
    Next
    INDEX
    Explanations

    adjectives describing positive experiences or qualities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wonderful" and its associated positive connotations

    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
    eki
    -0.91
    soDeliveryDate
    -0.86
    resy
    -0.82
    rict
    -0.77
    pai
    -0.74
    abus
    -0.74
    SEE
    -0.73
    avis
    -0.73
    arthed
    -0.73
    arettes
    -0.71
    POSITIVE LOGITS
     scenery
    0.86
     coincidence
    0.81
     young
    0.81
     opportunity
    0.79
     thing
    0.78
     gift
    0.78
     sounding
    0.75
     multicultural
    0.75
     memories
    0.73
     maiden
    0.73
    Activations Density 0.122%

    No Known Activations