© 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. 4-RES-JB
    11. 2705
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location, particularly involving the word "ver" as part of the word

    oai_token-act-pair · gpt-3.5-turbo

    instances and variations of the word "ver."

    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
    ENDED
    -0.77
    ollo
    -0.76
    Ĥª
    -0.74
    ixed
    -0.66
    akings
    -0.66
    erva
    -0.64
     Dietary
    -0.63
     pestic
    -0.63
    ourt
    -0.60
    ered
    -0.59
    POSITIVE LOGITS
    theless
    1.09
    dict
    1.09
    ver
    1.06
    gence
    1.06
    tex
    1.03
    deen
    0.93
    ledge
    0.85
    vier
    0.83
    ging
    0.82
    lisher
    0.81
    Activations Density 0.014%

    No Known Activations