© 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. 1-RES-JB
    11. 3569
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Bash" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emetery
    -0.80
    matter
    -0.75
    Scient
    -0.69
     unfocusedRange
    -0.67
     NCT
    -0.66
    ship
    -0.65
     Collider
    -0.64
    Civil
    -0.64
    Urban
    -0.64
    judicial
    -0.63
    POSITIVE LOGITS
     Bash
    1.34
    bash
    1.23
     bash
    1.20
    bolt
    0.80
    halla
    0.76
    pak
    0.76
    nikov
    0.75
    tty
    0.74
    thouse
    0.72
     curses
    0.72
    Activations Density 0.011%

    No Known Activations