© 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. 2-RES-JB
    11. 1068
    Prev
    Next
    INDEX
    Explanations

    terms related to gentrification

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gentrification and neighborhood revitalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uter
    -0.75
    esthes
    -0.74
     PUR
    -0.70
    /+
    -0.69
    ouple
    -0.68
    uters
    -0.68
    hus
    -0.68
    ISS
    -0.67
    legates
    -0.67
    aucus
    -0.65
    POSITIVE LOGITS
     revital
    1.24
     blight
    1.13
     neighbourhoods
    1.05
     redevelopment
    1.03
     neighborhoods
    0.98
     redevelop
    0.96
     gent
    0.91
    rification
    0.87
    scape
    0.83
     downtown
    0.83
    Activations Density 0.035%

    No Known Activations