© 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. 0-RES-JB
    11. 8177
    Prev
    Next
    INDEX
    Explanations

    mentions of neighborhoods

    oai_token-act-pair · gpt-3.5-turbo

    references to neighborhoods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emphas
    -0.79
     util
    -0.76
     Clive
    -0.75
     whilst
    -0.74
     practise
    -0.72
     apologise
    -0.71
     realised
    -0.70
    Cry
    -0.69
     Horus
    -0.69
     TIT
    -0.67
    POSITIVE LOGITS
     neighborhood
    3.65
     neighbourhood
    2.92
     Neighborhood
    2.47
     neighborhoods
    2.44
     neighbors
    1.92
     neighbor
    1.81
     neighbourhoods
    1.72
    Neigh
    1.71
     suburb
    1.69
     locality
    1.51
    Activations Density 0.011%

    No Known Activations