© 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. 2-RES-JB
    11. 8417
    Prev
    Next
    INDEX
    Explanations

    images

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "photo."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drawn
    -0.78
    sheet
    -0.77
    ded
    -0.62
     prosecution
    -0.62
    vertisement
    -0.60
    acious
    -0.60
    onyms
    -0.60
    breaking
    -0.59
    bread
    -0.59
    encers
    -0.59
    POSITIVE LOGITS
    zzi
    1.14
    amera
    0.98
    ÄŁ
    0.98
    veland
    0.95
    oga
    0.91
    ota
    0.87
    ña
    0.85
    oto
    0.85
    igslist
    0.82
    iba
    0.82
    Activations Density 0.009%

    No Known Activations