© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21169
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and dialogue

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, primarily commas

    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
    nesday
    -0.79
     corrid
    -0.72
    swick
    -0.72
    ilst
    -0.70
    æ©
    -0.68
    lead
    -0.65
    uces
    -0.63
    cuts
    -0.62
    oes
    -0.61
    ãĥ¯ãĥ³
    -0.61
    POSITIVE LOGITS
     undeniably
    0.68
     uh
    0.67
     Borough
    0.67
     alas
    0.67
     biologically
    0.66
     aest
    0.64
    yet
    0.64
    atown
    0.64
     barring
    0.63
    velength
    0.62
    Activations Density 0.133%

    No Known Activations