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. 9-RES-JB
    6. 21704
    Prev
    Next
    INDEX
    Explanations

    terms or phrases coined or used to describe certain concepts or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    terms and definitions used in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    htaking
    -0.76
    mits
    -0.67
    edient
    -0.65
    igators
    -0.65
    iencies
    -0.64
     Vaj
    -0.63
    phis
    -0.62
     cooperate
    -0.62
    psey
    -0.62
    iors
    -0.61
    POSITIVE LOGITS
     coined
    1.50
     slang
    1.24
     shorthand
    1.21
     synonymous
    1.16
     abbre
    1.09
     referring
    1.07
     acronym
    1.06
     uttered
    1.06
     interchange
    1.03
     derogatory
    1.01
    Activations Density 0.362%

    No Known Activations