© 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. 11-RES-JB
    11. 23949
    Prev
    Next
    INDEX
    Explanations

    phrases related to buildings and construction plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future plans or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cious
    -0.71
     VIDEOS
    -0.68
    Lear
    -0.68
    calling
    -0.67
    ontent
    -0.66
     Immunity
    -0.65
     MIS
    -0.64
    dylib
    -0.64
    retty
    -0.62
    summary
    -0.62
    POSITIVE LOGITS
     housed
    1.55
     houses
    1.29
     overlook
    1.26
     accommodate
    1.23
     accommod
    1.21
     house
    1.11
     hosts
    1.06
     reopened
    1.04
     hosted
    1.00
     seats
    0.99
    Activations Density 0.274%

    No Known Activations