© 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. 11388
    Prev
    Next
    INDEX
    Explanations

    words related to elevated outdoor spaces like "balcony" and "rooftop"

    oai_token-act-pair · gpt-3.5-turbo

    references to balconies and rooftops

    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
    govern
    -0.80
    alysis
    -0.75
    avez
    -0.72
    goo
    -0.71
    nesia
    -0.69
    chin
    -0.68
    commerce
    -0.67
    gan
    -0.67
    ciating
    -0.66
    veh
    -0.66
    POSITIVE LOGITS
     balcony
    1.23
     railing
    1.14
     balcon
    1.06
     patio
    0.91
     rooftop
    0.86
     lounge
    0.83
     overlooking
    0.77
     terr
    0.76
    deck
    0.73
     seating
    0.73
    Activations Density 0.017%

    No Known Activations