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. 17174
    Prev
    Next
    INDEX
    Explanations

    terms related to non-European immigrants and countries

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of non-state or non-mainstream groups and phenomena

    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
    CHAT
    -0.78
    Dialogue
    -0.74
    wagen
    -0.71
    AMS
    -0.68
    adder
    -0.68
    MAC
    -0.66
    Hope
    -0.65
    wark
    -0.64
    isu
    -0.61
    instead
    -0.61
    POSITIVE LOGITS
    ensical
    0.89
    ensable
    0.85
    theless
    0.83
    istant
    0.78
     nor
    0.78
    ables
    0.77
     whatsoever
    0.76
     anymore
    0.74
    existent
    0.74
    gment
    0.72
    Activations Density 0.072%

    No Known Activations