© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19755
    Prev
    Next
    INDEX
    Explanations

    academic, technical, or detailed language

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "require" and its variants, indicating a need or necessity

    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
    alde
    -0.86
    Sax
    -0.74
    rift
    -0.73
    =]
    -0.71
    olate
    -0.70
    owler
    -0.69
    oday
    -0.67
    edin
    -0.67
     Cheong
    -0.66
    ITED
    -0.66
    POSITIVE LOGITS
     approval
    0.85
     modification
    0.77
     patience
    0.76
     dexterity
    0.76
     intervention
    0.75
     attention
    0.74
     verification
    0.74
     skill
    0.74
     upkeep
    0.73
     authorization
    0.72
    Activations Density 0.145%

    No Known Activations