© 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. 2557
    Prev
    Next
    INDEX
    Explanations

    words related to business and sponsorship

    oai_token-act-pair · gpt-3.5-turbo

    instances of the "VP" acronym, indicating it is looking for references to official representatives or organizations

    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
     Galile
    -0.81
    bread
    -0.70
     critically
    -0.65
    obyl
    -0.63
     Pixar
    -0.62
    ©¶æ¥µ
    -0.60
     shallow
    -0.58
     tragically
    -0.58
     divorced
    -0.58
     Merlin
    -0.58
    POSITIVE LOGITS
    halla
    0.98
    atoon
    0.85
    isites
    0.85
    acebook
    0.82
    ignt
    0.81
    ione
    0.81
    isitions
    0.80
    anners
    0.77
    dx
    0.77
    ////
    0.76
    Activations Density 0.017%

    No Known Activations