© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5372
    Prev
    Next
    INDEX
    Explanations

    information related to online forum posts and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to posts and online activity metrics

    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
     tide
    -0.76
    unn
    -0.73
     match
    -0.70
     complement
    -0.68
     Nielsen
    -0.67
    oscope
    -0.65
    elsen
    -0.65
     exclusion
    -0.63
     gel
    -0.62
    ilic
    -0.61
    POSITIVE LOGITS
    Activity
    2.87
    Posts
    2.71
    Offline
    1.98
     Quote
    1.91
    Joined
    1.73
    talk
    1.56
    Quote
    1.53
     Logged
    1.25
    Registered
    1.22
    Merit
    1.21
    Activations Density 0.049%

    No Known Activations