© 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. 3-RES-JB
    11. 22852
    Prev
    Next
    INDEX
    Explanations

    phrases related to program outputs

    oai_token-act-pair · gpt-3.5-turbo

    references to "output" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.71
    anova
    -0.65
    Fort
    -0.64
    tones
    -0.63
    bite
    -0.63
    vette
    -0.62
     Blanc
    -0.60
    ETA
    -0.60
    atti
    -0.59
     Antiqu
    -0.59
    POSITIVE LOGITS
     output
    1.07
     outputs
    1.05
     Output
    0.99
    ted
    0.92
    ting
    0.86
    flows
    0.83
    rious
    0.83
    output
    0.82
    Output
    0.80
    flow
    0.78
    Activations Density 0.011%

    No Known Activations