© 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. 4-RES-JB
    11. 6380
    Prev
    Next
    INDEX
    Explanations

    phrases related to being well-matched or appropriate for a particular purpose or situation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to suitability or appropriateness for a given context or group

    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
     VIDEOS
    -0.78
    ãĥ£
    -0.65
     aborted
    -0.64
    agic
    -0.63
    dash
    -0.62
    inth
    -0.62
     NCT
    -0.61
    tery
    -0.60
    bish
    -0.59
    ä¼
    -0.59
    POSITIVE LOGITS
     suited
    0.92
    xual
    0.86
     fitt
    0.76
    folios
    0.74
     fit
    0.73
    ratulations
    0.71
     tailor
    0.69
    estro
    0.69
     compliment
    0.66
    glers
    0.65
    Activations Density 0.019%

    No Known Activations