© 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. 2-RES-JB
    11. 2404
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or place called "Rest."

    oai_token-act-pair · gpt-3.5-turbo

    references to rest in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åŃ
    -0.73
    ×Ļ×
    -0.71
     Kushner
    -0.66
    女
    -0.63
    Pear
    -0.61
    ×Ķ
    -0.61
    berus
    -0.60
    hua
    -0.59
    Î
    -0.59
    kers
    -0.59
    POSITIVE LOGITS
    ricted
    1.30
    raint
    1.25
    ricting
    1.08
    raining
    1.03
    raints
    1.02
    itution
    0.95
    rained
    0.94
    ructure
    0.94
    orative
    0.92
    ruct
    0.86
    Activations Density 0.008%

    No Known Activations