© 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. 23881
    Prev
    Next
    INDEX
    Explanations

    proper names or entities preceded by 'of'

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "of" followed by various numerical values or counts

    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
     agre
    -0.83
    ahime
    -0.73
     condem
    -0.66
     arrang
    -0.64
     misunder
    -0.63
    icultural
    -0.62
    rina
    -0.62
     surpr
    -0.61
     fert
    -0.61
    hend
    -0.61
    POSITIVE LOGITS
    teenth
    0.70
    ij士
    0.69
     dozen
    0.68
    teen
    0.66
    icial
    0.65
     finalists
    0.63
     Fulton
    0.63
    ources
    0.63
     UCLA
    0.62
    ife
    0.59
    Activations Density 0.072%

    No Known Activations