© 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. 9-RES-JB
    11. 14338
    Prev
    Next
    INDEX
    Explanations

    references to the concept of infinity or limitless quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to limitless or infinite quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acus
    -0.92
    iquette
    -0.90
    ector
    -0.78
    Reviewed
    -0.77
    ename
    -0.72
    bourg
    -0.71
    ective
    -0.71
    crow
    -0.70
    mast
    -0.70
    */(
    -0.70
    POSITIVE LOGITS
     amounts
    1.05
     regress
    0.98
     amount
    0.91
     repetition
    0.89
     supply
    0.88
     possibilities
    0.86
     quantities
    0.84
     loops
    0.82
     replay
    0.81
     Tsukuyomi
    0.81
    Activations Density 0.072%

    No Known Activations