© 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. 4-RES-JB
    11. 10464
    Prev
    Next
    INDEX
    Explanations

    phrases related to making serious allegations or accusations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "to be" in various forms

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

    No Comments

    Negative Logits
     Fair
    -0.63
     Starts
    -0.62
    jri
    -0.62
    eger
    -0.62
    sonian
    -0.62
    ital
    -0.62
    pedia
    -0.61
     Reports
    -0.61
     Details
    -0.61
    inis
    -0.60
    POSITIVE LOGITS
    nt
    1.02
     actually
    0.84
     never
    0.83
     somehow
    0.82
     truly
    0.81
     destined
    0.79
     purposely
    0.77
     indeed
    0.76
    NetMessage
    0.74
     genuinely
    0.74
    Activations Density 0.729%

    No Known Activations