© 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. 17054
    Prev
    Next
    INDEX
    Explanations

    instances of words related to processes or situations that involve a significant level of change or related terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of situations or conditions

    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
    die
    -0.80
    hold
    -0.76
    sol
    -0.71
    ebook
    -0.69
    leaf
    -0.67
    Sea
    -0.65
    artisan
    -0.65
    Co
    -0.65
    bi
    -0.63
    blue
    -0.62
    POSITIVE LOGITS
    uations
    1.67
    uation
    1.63
    uates
    1.44
    uating
    1.42
    uated
    1.41
    uate
    1.21
    alam
    0.88
    veyard
    0.79
    aution
    0.78
    terday
    0.78
    Activations Density 0.014%

    No Known Activations