© 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. 20395
    Prev
    Next
    INDEX
    Explanations

    people's names preceded by a title or context, likely in news articles or similar text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anti-ism or opposition

    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
     crawl
    -0.87
     numbered
    -0.74
     draw
    -0.73
     retail
    -0.67
     prompt
    -0.66
     matching
    -0.66
     reuse
    -0.65
     harness
    -0.63
     grow
    -0.63
     typ
    -0.62
    POSITIVE LOGITS
    anti
    4.51
    antis
    1.99
    Anti
    1.86
    ant
    1.51
    ante
    1.46
     Anti
    1.44
     anti
    1.41
    ANT
    1.38
    antine
    1.34
    anto
    1.31
    Activations Density 0.013%

    No Known Activations