© 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. 987
    Prev
    Next
    INDEX
    Explanations

    words with a root form of 'elude' or similar sounding endings like 'usion'

    oai_token-act-pair · gpt-4-turbo

    keywords related to concepts of exclusion or omission

    oai_token-act-pair · gpt-3.5-turbo

    words related to exclusion or omission

    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
    @#&
    -0.89
    rieve
    -0.77
    pora
    -0.73
     pressing
    -0.61
     reopened
    -0.60
    wood
    -0.59
     else
    -0.59
     sailed
    -0.58
    Ü
    -0.58
     commute
    -0.57
    POSITIVE LOGITS
    geoning
    0.96
    udes
    0.93
    uding
    0.93
    uded
    0.82
     Canaver
    0.78
    inous
    0.77
    éĹĺ
    0.77
    oldemort
    0.75
    geon
    0.75
    itives
    0.74
    Activations Density 0.013%

    No Known Activations