© 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. 2668
    Prev
    Next
    INDEX
    Explanations

    phrases containing conjunctions, often 'and'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "and" indicating connections or relationships between ideas

    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
    ummer
    -0.80
    atan
    -0.74
    utor
    -0.71
    qqa
    -0.69
    anmar
    -0.67
    EMS
    -0.65
    uto
    -0.65
    BAT
    -0.64
    umo
    -0.64
    qu
    -0.63
    POSITIVE LOGITS
     wondered
    1.08
     wished
    0.98
     urge
    0.96
     knew
    0.93
     wants
    0.89
     urges
    0.88
     knows
    0.88
     believes
    0.86
     wanted
    0.85
     wishes
    0.83
    Activations Density 0.315%

    No Known Activations