© 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. 2-RES-JB
    11. 5506
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    named entities or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.73
    hips
    -0.73
    zona
    -0.72
    rio
    -0.71
    hold
    -0.70
    è¦ļéĨĴ
    -0.68
    thumbnails
    -0.68
    mir
    -0.67
    ingham
    -0.67
    borgh
    -0.66
    POSITIVE LOGITS
    NP
    1.11
     NP
    0.86
    ublic
    0.83
    emonic
    0.83
    ointed
    0.80
    olicy
    0.79
    PP
    0.76
    oint
    0.76
    rint
    0.75
    EED
    0.74
    Activations Density 0.007%

    No Known Activations