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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 23741
    Prev
    Next
    INDEX
    Explanations

    abbreviations that start with 'C' and end with 'OO'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of corporate entities, particularly with reference to their executive roles and organizational structures

    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
    flies
    -0.86
     Newsp
    -0.78
    usa
    -0.75
    ulia
    -0.74
    icity
    -0.71
    Links
    -0.69
    veh
    -0.68
    wikipedia
    -0.68
    wick
    -0.68
     Indones
    -0.67
    POSITIVE LOGITS
    IAL
    0.91
    GY
    0.89
    OOL
    0.86
    OO
    0.85
    ODUCT
    0.81
    OTS
    0.76
    VERTISEMENT
    0.75
    FU
    0.75
    BY
    0.73
     accountant
    0.73
    Activations Density 0.021%

    No Known Activations