© 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. 10567
    Prev
    Next
    INDEX
    Explanations

    references to seasonal changes, specific dates, and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to seasonal changes and various scientific or technical concepts

    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
    iphate
    -0.78
    mma
    -0.77
    cko
    -0.71
    ramid
    -0.70
    PRES
    -0.67
    aeda
    -0.67
    endment
    -0.67
    oji
    -0.66
    ovie
    -0.65
    qt
    -0.63
    POSITIVE LOGITS
     historians
    0.77
     analysts
    0.73
     versions
    0.69
     quantities
    0.68
    inarily
    0.68
     theorists
    0.67
     programmers
    0.67
    ortunately
    0.67
    bugs
    0.66
     buffs
    0.65
    Activations Density 0.760%

    No Known Activations