© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23729
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant event or decline

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "down."

    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
    ilies
    -0.80
    Us
    -0.77
    ¶ħ
    -0.70
    iliary
    -0.70
    ature
    -0.67
    digy
    -0.64
    velt
    -0.64
    iler
    -0.63
    jamin
    -0.61
    anooga
    -0.61
    POSITIVE LOGITS
     stairs
    1.10
    graded
    1.04
    grading
    0.90
    stairs
    0.90
    river
    0.85
     horm
    0.84
    LOAD
    0.80
    hill
    0.73
     hill
    0.73
    wind
    0.72
    Activations Density 0.032%

    No Known Activations