© 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. 8-RES-JB
    11. 14993
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be"

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rones
    -0.78
    culosis
    -0.74
    anwhile
    -0.74
    rouse
    -0.70
    rella
    -0.68
    inav
    -0.67
     illuminate
    -0.65
    iasco
    -0.64
     rall
    -0.62
    ãĥ¼ãĥ«
    -0.62
    POSITIVE LOGITS
     able
    0.96
    leeve
    0.81
     influenced
    0.77
     helpful
    0.76
     quite
    0.74
     considered
    0.71
     biased
    0.71
     regarded
    0.71
    falls
    0.70
     extremely
    0.70
    Activations Density 0.116%

    No Known Activations