Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 15560
    Prev
    Next
    INDEX
    Explanations

    mentions of rooftops or related rooftop activities

    oai_token-act-pair · gpt-3.5-turbo

    references to rooftop solar installations and related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avez
    -0.86
    nesia
    -0.82
    gans
    -0.78
    thia
    -0.75
    apolis
    -0.72
    odor
    -0.71
     Larson
    -0.70
    Canadian
    -0.70
    sen
    -0.69
    Sym
    -0.68
    POSITIVE LOGITS
     rooftop
    1.31
     balcon
    1.07
     balcony
    1.03
     rooft
    0.98
     roof
    0.89
     patio
    0.89
     railing
    0.86
     terr
    0.86
     loft
    0.86
     alley
    0.84
    Activations Density 0.012%

    No Known Activations