© 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. 15843
    Prev
    Next
    INDEX
    Explanations

    locations or places, particularly neighborhoods and landmarks

    oai_token-act-pair · gpt-3.5-turbo

    locations and references to geographical places or events

    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
    ĨĴ
    -0.80
    elta
    -0.66
    ħĭ
    -0.64
    é¾įå
    -0.63
     behalf
    -0.56
    adi
    -0.55
    ymes
    -0.55
    ÃŃ
    -0.55
    umi
    -0.54
    cffff
    -0.53
    POSITIVE LOGITS
     on
    1.57
    on
    1.42
    On
    1.39
     ON
    1.36
     On
    1.35
     onto
    1.16
    ons
    1.11
    ON
    1.06
     upon
    1.01
    upon
    0.98
    Activations Density 0.301%

    No Known Activations