© 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. 15281
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty or challenge

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate difficulty or challenges

    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
    Introduced
    -0.68
    KK
    -0.67
    Champ
    -0.66
    Sham
    -0.64
    ONSORED
    -0.64
    mare
    -0.62
    fleet
    -0.61
    BM
    -0.61
    cles
    -0.60
    killed
    -0.60
    POSITIVE LOGITS
    bidden
    1.21
    gotten
    1.21
    geries
    1.17
    gery
    1.15
     example
    1.10
     instance
    1.03
     purposes
    0.98
    aging
    0.97
     starters
    0.93
    ked
    0.91
    Activations Density 0.495%

    No Known Activations