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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16558
    Prev
    Next
    INDEX
    Explanations

    terms related to temporary positions or arrangements

    oai_token-act-pair · gpt-3.5-turbo

    references to temporary or provisional roles and conditions

    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
    gling
    -0.98
    rera
    -0.81
    Club
    -0.80
    plex
    -0.79
    wagen
    -0.76
    ku
    -0.76
    kie
    -0.76
    beer
    -0.73
    licks
    -0.73
    ggies
    -0.72
    POSITIVE LOGITS
     interim
    1.02
     truce
    0.77
     measures
    0.75
    etheless
    0.75
     responders
    0.74
    ities
    0.70
     Measures
    0.70
    TY
    0.68
     periods
    0.66
     declarations
    0.65
    Activations Density 0.009%

    No Known Activations