© 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. 7430
    Prev
    Next
    INDEX
    Explanations

    references to urban environments, particularly streets

    oai_token-act-pair · gpt-3.5-turbo

    references to 'streets' and urban environments

    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
    ASED
    -0.59
     compr
    -0.57
    Ī
    -0.57
     Species
    -0.56
    otide
    -0.56
    Status
    -0.55
    -+-+
    -0.54
    emort
    -0.53
     Pru
    -0.52
    oni
    -0.52
    POSITIVE LOGITS
    cape
    1.34
    creen
    1.20
    pace
    1.15
    pring
    1.14
     of
    1.13
    chool
    1.09
    ide
    1.07
    hip
    1.07
    hift
    1.06
    mith
    1.05
    Activations Density 0.243%

    No Known Activations