© 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. 23061
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating value judgments

    oai_token-act-pair · gpt-3.5-turbo

    words that describe legitimacy and recent occurrences

    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
    anders
    -0.71
    aimon
    -0.69
    ADS
    -0.68
    andering
    -0.68
    avez
    -0.65
    adr
    -0.64
    UGE
    -0.64
    agine
    -0.63
    REL
    -0.62
    antics
    -0.61
    POSITIVE LOGITS
    ly
    2.53
    LY
    1.56
    liness
    1.31
    lys
    1.25
    edly
    1.15
    fully
    1.12
    lies
    1.11
    ELY
    1.09
    liest
    1.02
    ity
    1.00
    Activations Density 0.077%

    No Known Activations