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

    Neuronpedia

    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. 55
    Prev
    Next
    INDEX
    Explanations

    terms related to housing and property development

    oai_token-act-pair · gpt-3.5-turbo

    topics related to urban development and housing issues

    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
    orah
    -0.75
    verning
    -0.74
    ename
    -0.70
    escription
    -0.69
    apixel
    -0.67
    hift
    -0.67
    linger
    -0.66
    abella
    -0.66
     earthqu
    -0.66
    ĸļ
    -0.65
    POSITIVE LOGITS
     scenarios
    1.39
     schemes
    1.36
     situations
    1.33
     packages
    1.31
     items
    1.30
    pieces
    1.29
     tracts
    1.27
     platforms
    1.25
     programs
    1.25
     pieces
    1.25
    Activations Density 0.682%

    No Known Activations