© 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. 0-RES-JB
    11. 2905
    Prev
    Next
    INDEX
    Explanations

    specific terms like "Ratification", "Pellets", and "Bids"

    oai_token-act-pair · gpt-3.5-turbo

    references to ratings or evaluations, particularly in the context of media or entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Limited
    -0.66
     Cind
    -0.64
    Sword
    -0.64
     Eclipse
    -0.63
     Columb
    -0.62
     repositories
    -0.61
    GN
    -0.59
     specimens
    -0.58
    Interested
    -0.58
    Textures
    -0.58
    POSITIVE LOGITS
    Rat
    1.40
    bid
    0.80
    earance
    0.77
     contend
    0.76
    atown
    0.76
    alities
    0.75
    gat
    0.74
     beware
    0.69
    effic
    0.69
    uchin
    0.69
    Activations Density 0.001%

    No Known Activations