© 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. 14346
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by descriptions or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "but" indicating contrast or contradiction

    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
    umat
    -0.78
    ermanent
    -0.70
    Optional
    -0.69
    amus
    -0.66
    itto
    -0.64
    ħĭ
    -0.63
    matter
    -0.63
    pec
    -0.62
    agan
    -0.61
    gged
    -0.61
    POSITIVE LOGITS
     luckily
    1.13
     fortunately
    1.10
     alas
    1.04
     nevertheless
    0.98
     lately
    0.94
     thankfully
    0.92
     nonetheless
    0.90
     unfortunately
    0.82
     sadly
    0.77
    chers
    0.77
    Activations Density 0.160%

    No Known Activations