© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24011
    Prev
    Next
    INDEX
    Explanations

    references to software libraries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "library" and its variations

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

    No Comments

    Negative Logits
     Samoa
    -0.72
    ilon
    -0.71
    irin
    -0.69
    pid
    -0.68
    Pacific
    -0.65
    lyak
    -0.65
    ederal
    -0.64
    empt
    -0.63
    lv
    -0.62
     Gaia
    -0.62
    POSITIVE LOGITS
    oaded
    0.80
    ibraries
    0.77
    matically
    0.77
    DragonMagazine
    0.76
    inary
    0.75
     dumps
    0.75
     library
    0.73
     runtime
    0.73
    istry
    0.72
     libraries
    0.72
    Activations Density 0.013%

    No Known Activations