© 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. 983
    Prev
    Next
    INDEX
    Explanations

    the word stem "sl" at the beginning of words

    oai_token-act-pair · gpt-4-turbo

    words related to slippery or slimy textures or situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sl" 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
    ICLE
    -0.91
    enegger
    -0.77
    heid
    -0.73
     Continued
    -0.71
     Cause
    -0.70
    éļ
    -0.69
    IFIC
    -0.68
     EVENT
    -0.66
     DeVos
    -0.65
    ruary
    -0.64
    POSITIVE LOGITS
    udge
    1.11
    ither
    1.09
    anted
    1.07
    asher
    1.05
    ugg
    1.04
    inking
    1.04
    ashed
    1.01
    umber
    0.97
    ashes
    0.97
    udging
    0.96
    Activations Density 0.009%

    No Known Activations