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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5340
    Prev
    Next
    INDEX
    Explanations

    phrases related to transportation or movement onto a vehicle or mode of travel

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "boarding" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icity
    -0.82
    encers
    -0.80
    ifer
    -0.77
    lly
    -0.77
     recession
    -0.70
    tymology
    -0.69
    encer
    -0.65
    ascus
    -0.64
    uments
    -0.63
    ensional
    -0.63
    POSITIVE LOGITS
     boarding
    1.19
    walk
    1.01
    wal
    0.97
    folios
    0.89
    boarding
    0.88
    crew
    0.87
    ĵĺ
    0.86
    rooms
    0.81
    mares
    0.80
    stars
    0.80
    Activations Density 0.020%

    No Known Activations