© 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. 6-RES-JB
    11. 14834
    Prev
    Next
    INDEX
    Explanations

    names of people and events related to significant life changes or political actions

    oai_token-act-pair · gpt-3.5-turbo

    key events and significant details related to personal and financial circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amate
    -0.56
    tein
    -0.56
    spir
    -0.53
    dra
    -0.51
    pta
    -0.51
    onsense
    -0.50
    ews
    -0.49
    é¾įåĸļ士
    -0.48
    å¦
    -0.46
    Wr
    -0.46
    POSITIVE LOGITS
     astronomers
    0.52
     interven
    0.50
    Poké
    0.49
    Enlarge
    0.49
     Morty
    0.47
    RON
    0.46
     Esther
    0.46
     shielding
    0.46
     Telegram
    0.44
     pressuring
    0.44
    Activations Density 1.557%

    No Known Activations