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. 2402
    Prev
    Next
    INDEX
    Explanations

    Russian-related words or phrases specifically containing the characters "Ð" or "Ñ"

    oai_token-act-pair · gpt-3.5-turbo

    characters or symbols commonly used in a specific language or textual format

    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
    cheon
    -0.82
    nings
    -0.81
    gio
    -0.77
    mber
    -0.71
    blems
    -0.70
    hyde
    -0.70
    vision
    -0.67
    tten
    -0.65
    ptions
    -0.65
    ple
    -0.64
    POSITIVE LOGITS
    ÑĮ
    0.94
    NetMessage
    0.85
    omething
    0.81
    essor
    0.81
    ĩ
    0.78
    hak
    0.75
    inger
    0.75
    inator
    0.74
    onne
    0.74
    Ĭ
    0.73
    Activations Density 0.019%

    No Known Activations