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. 24269
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "OU" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term related to the concept of 'output'

    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
    ãĤ¹ãĥĪ
    -0.78
    ãĥŁ
    -0.75
    ãĥ¼ãĥĨãĤ£
    -0.69
     Cobra
    -0.68
    ãĥĵ
    -0.67
    ãĤº
    -0.66
    ãĤ¢ãĥ«
    -0.66
     Kraken
    -0.66
    ãĥķãĤ©
    -0.65
     Birch
    -0.64
    POSITIVE LOGITS
    BLE
    1.02
    PDATE
    0.98
    LET
    0.92
    OTUS
    0.89
    TERN
    0.88
    ser
    0.85
    lisher
    0.85
    terness
    0.85
    VEN
    0.85
    UU
    0.83
    Activations Density 0.009%

    No Known Activations