© 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. 0-RES-JB
    11. 22456
    Prev
    Next
    INDEX
    Explanations

    words ending in "ils" at the end of phrases or sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "ils" and its variations, indicating a focus on plural forms or instances of this term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BET
    -0.71
     floor
    -0.62
     scholarship
    -0.61
     Baptist
    -0.60
     bar
    -0.60
     --------------------------------
    -0.60
     allot
    -0.59
     selective
    -0.59
     spot
    -0.59
    ãģ®ç
    -0.58
    POSITIVE LOGITS
    ils
    4.81
    ILS
    2.41
    il
    2.14
    iling
    2.05
    iled
    1.94
    IL
    1.75
    iles
    1.71
    ilings
    1.62
    ilities
    1.58
    ilic
    1.53
    Activations Density 0.006%

    No Known Activations