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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 14698
    Prev
    Next
    INDEX
    Explanations

    words related to the chemical compound "meth"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "eth"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clement
    -0.72
     Vaj
    -0.64
    edom
    -0.63
     tact
    -0.60
    yrinth
    -0.57
     targets
    -0.57
     exceptional
    -0.57
    xual
    -0.56
     Samoa
    -0.56
    hips
    -0.56
    POSITIVE LOGITS
    lehem
    1.57
    ulhu
    1.27
    oven
    1.15
    iop
    1.09
    rower
    1.08
    amphetamine
    1.08
    anasia
    1.06
    icone
    1.04
    anol
    1.03
    urst
    1.01
    Activations Density 0.046%

    No Known Activations