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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10637
    Prev
    Next
    INDEX
    Explanations

    special characters and numbers which do not seem to form any specific pattern or meaningful text

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.80
    soDeliveryDate
    -0.71
     scrut
    -0.59
    aviour
    -0.55
    çīĪ
    -0.54
     sugg
    -0.52
    urnal
    -0.52
    sonian
    -0.52
    zsche
    -0.50
    ologies
    -0.50
    POSITIVE LOGITS
    istan
    0.60
    ello
    0.59
    Ö¼
    0.52
     rice
    0.50
    à¨
    0.50
    assi
    0.49
    ibal
    0.49
     measles
    0.49
     Patty
    0.46
    esi
    0.45
    Activations Density 1.044%

    No Known Activations