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. 0-RES-JB
    6. 4242
    Prev
    Next
    INDEX
    Explanations

    words related to numbers or counting

    oai_token-act-pair · gpt-3.5-turbo

    words related to ordinal numbers, particularly "eighth" and "ninth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Libre
    -0.65
     Demand
    -0.64
     Ag
    -0.64
     gas
    -0.64
     processes
    -0.61
     ag
    -0.61
     machines
    -0.61
     sketch
    -0.60
     melting
    -0.59
     Flor
    -0.59
    POSITIVE LOGITS
    ighth
    4.99
    inth
    1.44
    venth
    1.39
    IGHTS
    1.36
    ights
    1.21
    ighthouse
    1.15
    elfth
    1.14
    ieth
    1.10
    enth
    1.09
    ngth
    1.04
    Activations Density 0.011%

    No Known Activations