© 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. 15222
    Prev
    Next
    INDEX
    Explanations

    terms related to dining or eating establishments

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "at" followed by various numerical references, indicating locations or times

    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
    FTWARE
    -0.77
    vous
    -0.71
    ctor
    -0.67
    released
    -0.67
    oulos
    -0.66
    lda
    -0.66
    Pac
    -0.65
    archy
    -0.64
    zyk
    -0.64
    Lens
    -0.64
    POSITIVE LOGITS
     least
    1.22
    yp
    0.97
    onement
    0.97
     halftime
    0.90
     home
    0.88
    abase
    0.86
     weekends
    0.85
    mosp
    0.85
     cafes
    0.82
     intervals
    0.81
    Activations Density 0.222%

    No Known Activations