© 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. 3-RES-JB
    11. 15211
    Prev
    Next
    INDEX
    Explanations

    mentions of condominiums

    oai_token-act-pair · gpt-3.5-turbo

    references to condominium and housing-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Published
    -0.76
    =-=-=-=-=-=-=-=-
    -0.74
    saf
    -0.74
    à¥
    -0.65
    nesses
    -0.65
    ym
    -0.65
    poll
    -0.64
    mic
    -0.64
    alter
    -0.64
    ker
    -0.63
    POSITIVE LOGITS
     condos
    1.26
     condo
    1.20
    ominium
    1.09
     apartments
    1.07
     rentals
    0.94
     occupancy
    0.93
     apartment
    0.90
    rete
    0.89
     rental
    0.87
     towers
    0.84
    Activations Density 0.011%

    No Known Activations