© 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. 6252
    Prev
    Next
    INDEX
    Explanations

    positive superlatives indicating excellence

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives indicating high quality or value

    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
    appings
    -0.80
    é¾į
    -0.78
    ymes
    -0.77
    ourning
    -0.76
    rahim
    -0.73
    adders
    -0.70
    asions
    -0.70
    èĪ
    -0.68
    ancies
    -0.68
    iencies
    -0.68
    POSITIVE LOGITS
     thing
    1.18
     predictor
    0.97
     ever
    0.96
     conceivable
    0.93
     imaginable
    0.92
     EVER
    0.85
     example
    0.83
     piece
    0.81
     sounding
    0.81
     indicator
    0.81
    Activations Density 0.164%

    No Known Activations