© 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. 1222
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to legal documents or procedures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bombo" or its variants

    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
     postage
    -0.65
     branches
    -0.62
     squared
    -0.60
     Nish
    -0.59
     Nationals
    -0.59
     patches
    -0.59
     recess
    -0.58
     Ul
    -0.58
     contents
    -0.57
     HD
    -0.57
    POSITIVE LOGITS
    bo
    4.35
    bos
    2.23
    Bo
    1.83
    BO
    1.76
     Bo
    1.52
    Boo
    1.44
     bo
    1.41
     BO
    1.33
    bon
    1.32
    bs
    1.32
    Activations Density 0.016%

    No Known Activations