© 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. 11-RES-JB
    11. 7437
    Prev
    Next
    INDEX
    Explanations

    words related to physical locations or infrastructure, specifically pedestrian areas

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "estrian" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     impe
    -0.59
    shock
    -0.56
     Bain
    -0.55
    going
    -0.54
    kefeller
    -0.54
     Yates
    -0.53
     faculties
    -0.53
    clusive
    -0.53
    plates
    -0.53
    employed
    -0.53
    POSITIVE LOGITS
    rian
    1.24
    ruct
    1.21
    reet
    1.19
    imate
    1.17
    rians
    1.16
    oppers
    1.15
    ream
    1.15
    hetics
    1.12
    rations
    1.08
    imates
    1.06
    Activations Density 0.050%

    No Known Activations