© 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. 12610
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific organization or location

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and periods

    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
    ashtra
    -0.71
    anova
    -0.68
    allery
    -0.66
    osal
    -0.65
    rawdownloadcloneembedreportprint
    -0.64
    hari
    -0.63
     srfAttach
    -0.63
    oodle
    -0.63
    oola
    -0.62
    atu
    -0.62
    POSITIVE LOGITS
     coli
    1.30
     Coy
    0.74
     Moss
    0.73
     Tec
    0.70
    gypt
    0.69
     Pas
    0.69
     Romero
    0.67
     pas
    0.66
    TERN
    0.65
    tainment
    0.65
    Activations Density 0.051%

    No Known Activations