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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 2090
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals with variations of the name "Timmons"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific "mn" or "mons" phrases and references related to religious or community sermons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lara
    -0.72
     Pall
    -0.70
    ourgeois
    -0.63
     Maya
    -0.62
     CGI
    -0.61
     reconc
    -0.61
     Syndicate
    -0.60
     complex
    -0.59
    holding
    -0.59
     Complex
    -0.59
    POSITIVE LOGITS
    iasm
    1.12
     ILCS
    0.92
    waukee
    0.89
    ãĥ£
    0.86
    MN
    0.85
    onso
    0.84
    ifest
    0.84
    maxwell
    0.83
    nesota
    0.82
    iem
    0.78
    Activations Density 0.024%

    No Known Activations