© 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. 7-RES-JB
    11. 10027
    Prev
    Next
    INDEX
    Explanations

    abbreviations or acronyms followed by their corresponding expansions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "or"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rue
    -0.80
    arten
    -0.78
    erest
    -0.77
    ileaks
    -0.77
    ires
    -0.75
    aretz
    -0.73
    estro
    -0.73
    onday
    -0.68
    olicy
    -0.68
    rodu
    -0.68
    POSITIVE LOGITS
    chard
    1.12
    acle
    1.00
     alternatively
    0.99
    acles
    0.89
    chid
    0.87
    ifice
    0.85
    chest
    0.84
    GAN
    0.82
    acular
    0.82
    ific
    0.79
    Activations Density 0.071%

    No Known Activations