© 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. 4-RES-JB
    11. 14777
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to healthcare settings or professions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Care" and its variations

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

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.79
     perjury
    -0.65
     extrad
    -0.62
     awe
    -0.62
    integer
    -0.62
    RESULTS
    -0.61
     sql
    -0.61
     lap
    -0.61
     Chomsky
    -0.59
     poppy
    -0.58
    POSITIVE LOGITS
    taker
    1.30
    care
    0.98
    giving
    0.98
    er
    0.97
    fully
    0.96
    tta
    0.87
    ndra
    0.86
    lli
    0.86
    llan
    0.85
    taking
    0.83
    Activations Density 0.014%

    No Known Activations