© 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. 6397
    Prev
    Next
    INDEX
    Explanations

    names related to the Saxons and specific terms such as 'Sax', 'Wald', and 'cheek'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of musical instruments and specific names

    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
     soluble
    -0.66
    ITE
    -0.65
    opsis
    -0.65
    leased
    -0.64
     Podesta
    -0.63
     tuna
    -0.63
    ISO
    -0.63
    ascus
    -0.62
    ablo
    -0.59
    asta
    -0.59
    POSITIVE LOGITS
    ophon
    1.01
    ophone
    0.94
    es
    0.87
    schild
    0.86
    ynski
    0.80
    ander
    0.78
    ant
    0.78
    sv
    0.75
    atile
    0.74
    shire
    0.74
    Activations Density 0.080%

    No Known Activations