© 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. 9-RES-JB
    11. 19967
    Prev
    Next
    INDEX
    Explanations

    references to a location or entity named "Villa"

    oai_token-act-pair · gpt-3.5-turbo

    the mention of "Vill" followed by a number, indicating a focus on specific entities or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.76
    çķ
    -0.76
    à¥
    -0.68
     pelvic
    -0.63
     Mik
    -0.61
     silence
    -0.59
     Pax
    -0.59
     tong
    -0.59
    ãĥ¼ãĤ¯
    -0.59
    ा
    -0.59
    POSITIVE LOGITS
    anova
    1.50
    iage
    1.36
    agers
    1.26
    ains
    1.19
    ages
    1.19
    ain
    1.13
    ager
    1.05
    aine
    1.03
    age
    0.97
    agic
    0.95
    Activations Density 0.048%

    No Known Activations