© 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. 7-RES-JB
    11. 18090
    Prev
    Next
    INDEX
    Explanations

    propper nouns

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and terms related to significant social issues and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rack
    -0.77
     Kinnikuman
    -0.64
     Amendments
    -0.63
     Vertical
    -0.62
    Platform
    -0.60
     Shore
    -0.60
     Crunch
    -0.60
     Staten
    -0.59
    hap
    -0.59
    stanbul
    -0.58
    POSITIVE LOGITS
    matically
    0.80
    ically
    0.80
    rily
    0.78
    ishly
    0.73
    tarians
    0.73
    cause
    0.71
    inately
    0.71
    ises
    0.69
    ifies
    0.69
    heartedly
    0.68
    Activations Density 0.732%

    No Known Activations