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. 0-RES-JB
    6. 3853
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical processes involving fixing or sorting things out

    oai_token-act-pair · gpt-3.5-turbo

    words related to "iling" (such as filing, compiling, and similar forms)

    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
     Observer
    -0.66
     Dunk
    -0.60
     originated
    -0.60
     Conquest
    -0.59
     expl
    -0.59
     scales
    -0.58
    marks
    -0.58
     amen
    -0.57
     instant
    -0.57
     js
    -0.56
    POSITIVE LOGITS
    iling
    4.54
    iled
    3.06
    ilings
    2.41
    iler
    2.23
    ilers
    2.17
    ils
    2.12
    iles
    2.05
    ilation
    1.72
    ile
    1.70
    il
    1.48
    Activations Density 0.011%

    No Known Activations