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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 20220
    Prev
    Next
    INDEX
    Explanations

    details related to urban development projects

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of urban development projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Virus
    -0.84
     saliva
    -0.83
    ERROR
    -0.79
     whip
    -0.77
    errors
    -0.73
     pse
    -0.73
     flu
    -0.73
    emia
    -0.71
     infections
    -0.71
    nikov
    -0.70
    POSITIVE LOGITS
     redevelop
    1.46
     redevelopment
    1.43
     renovation
    1.23
     renovations
    1.18
     landsc
    1.15
     plaza
    1.13
    Construction
    1.13
     waterfront
    1.13
     renovated
    1.12
     construction
    1.11
    Activations Density 0.972%

    No Known Activations