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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 18735
    Prev
    Next
    INDEX
    Explanations

    dates in numerical format

    oai_token-act-pair · gpt-3.5-turbo

    numeric values related to dates and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orius
    -0.77
    fall
    -0.76
    teenth
    -0.72
    ions
    -0.71
    omic
    -0.70
    olate
    -0.68
    urated
    -0.67
    intosh
    -0.65
    hyde
    -0.65
    ype
    -0.63
    POSITIVE LOGITS
    nd
    2.27
    ND
    1.31
    ndra
    0.95
    nda
    0.86
    lr
    0.78
    50
    0.76
    nder
    0.76
    rd
    0.75
    NO
    0.72
    een
    0.70
    Activations Density 0.095%

    No Known Activations