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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 24039
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific term "Av"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Av" and related terms, indicating a focus on a specific entity or brand associated with those occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenant
    -0.72
    hyde
    -0.67
     respons
    -0.64
    FORMATION
    -0.63
    ciplinary
    -0.63
     Portsmouth
    -0.62
    bered
    -0.61
     Coke
    -0.60
    ptives
    -0.60
     inaccessible
    -0.60
    POSITIVE LOGITS
    ocado
    1.16
    atars
    1.15
    ril
    1.10
    iew
    1.07
    iator
    1.06
    iol
    1.02
    iations
    1.02
    raham
    1.00
    atar
    0.99
    ionics
    0.98
    Activations Density 0.021%

    No Known Activations