© 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. 993
    Prev
    Next
    INDEX
    Explanations

    the word "First" at the beginning of a sentence or sequence

    oai_token-act-pair · gpt-4-turbo

    the word "First" at the beginning of passages

    oai_token-act-pair · gpt-3.5-turbo

    the word "First" 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
    âĹ¼
    -0.65
    sav
    -0.63
    mens
    -0.62
    pers
    -0.61
    android
    -0.61
    ucl
    -0.60
    vor
    -0.60
    chrom
    -0.59
    health
    -0.59
    god
    -0.59
    POSITIVE LOGITS
     responders
    0.95
     baseman
    0.85
     blush
    0.83
     arri
    0.77
     glance
    0.77
    etheless
    0.76
    aturdays
    0.76
     ancest
    0.76
     installment
    0.75
     Encounter
    0.75
    Activations Density 0.069%

    No Known Activations