Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2883
    Prev
    Next
    INDEX
    Explanations

    references to historical or fictional figures associated with crusades

    oai_token-act-pair · gpt-3.5-turbo

    references to crusades or crusaders, particularly in a socio-political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regulated
    -0.71
    ocre
    -0.71
    ERAL
    -0.70
    esthesia
    -0.69
    nosis
    -0.68
    specified
    -0.68
     resid
    -0.68
    RAW
    -0.67
    selection
    -0.67
    stood
    -0.67
    POSITIVE LOGITS
     Crusade
    1.04
     crus
    0.98
    aders
    0.92
     crusade
    0.86
     zeal
    0.82
    ader
    0.78
    crow
    0.77
    andise
    0.74
     heats
    0.73
    onte
    0.71
    Activations Density 0.029%

    No Known Activations