© 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. 3-RES-JB
    11. 10670
    Prev
    Next
    INDEX
    Explanations

    notable or important pieces of information

    oai_token-act-pair · gpt-3.5-turbo

    references to "tips" and suggestions related to various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Asylum
    -0.72
     Recall
    -0.70
    ruciating
    -0.68
     Zed
    -0.67
     Spears
    -0.66
     Palest
    -0.66
     CN
    -0.66
     NAME
    -0.64
     Refugee
    -0.62
     ILCS
    -0.62
    POSITIVE LOGITS
     tip
    1.42
    tip
    1.35
     tips
    1.04
    Tip
    1.00
     tipped
    0.98
    tips
    0.97
     Tip
    0.89
     tipping
    0.87
     jar
    0.84
    idon
    0.82
    Activations Density 0.010%

    No Known Activations