© 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. 9324
    Prev
    Next
    INDEX
    Explanations

    information related to dropdown menus or options on a website

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "down" in various contexts

    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
     fabricated
    -0.69
     utmost
    -0.66
    aleigh
    -0.66
     openings
    -0.66
     authentic
    -0.65
    ĸļ
    -0.64
    asio
    -0.63
     expend
    -0.62
    ://
    -0.62
     inventive
    -0.62
    POSITIVE LOGITS
    stairs
    1.55
    dates
    1.07
    down
    1.06
    LOAD
    1.02
    hill
    1.02
    loaded
    0.99
    graded
    0.96
    grading
    0.93
    grades
    0.90
    fall
    0.89
    Activations Density 0.007%

    No Known Activations