© 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. 7-RES-JB
    11. 12384
    Prev
    Next
    INDEX
    Explanations

    Spanish words with accent marks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific accented characters in names or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsk
    -0.71
     Ellison
    -0.69
     guiActiveUnfocused
    -0.67
    ORED
    -0.65
     wedge
    -0.63
     Crus
    -0.63
     levers
    -0.63
    ++++
    -0.63
    pread
    -0.63
    orial
    -0.62
    POSITIVE LOGITS
    rio
    1.18
    vez
    1.03
    rez
    1.03
    ration
    0.97
    ndum
    0.95
    ternity
    0.91
    lean
    0.89
    ï
    0.85
    ñ
    0.84
    rica
    0.82
    Activations Density 0.020%

    No Known Activations