© 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. 1-RES-JB
    6. 11269
    Prev
    Next
    INDEX
    Explanations

    references to historical or fictional figures associated with the term 'crusaders'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to crusading figures or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retri
    -0.69
     Kaufman
    -0.69
     Lal
    -0.69
     Cly
    -0.66
     joint
    -0.66
     Sit
    -0.65
     Hath
    -0.62
     partnership
    -0.62
     Barton
    -0.62
     LIFE
    -0.62
    POSITIVE LOGITS
    aders
    1.39
    aneers
    0.89
    istors
    0.89
    chool
    0.87
    wikipedia
    0.83
    words
    0.83
     Parables
    0.80
    heet
    0.80
    word
    0.79
    aints
    0.78
    Activations Density 0.013%

    No Known Activations