© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2038
    Prev
    Next
    INDEX
    Explanations

    phrases related to options or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to effective methods or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.66
    uckles
    -0.58
    anwhile
    -0.56
    ridor
    -0.55
     Mub
    -0.55
    ornings
    -0.54
     afterward
    -0.53
    yrs
    -0.52
    opol
    -0.52
     lest
    -0.52
    POSITIVE LOGITS
     cryptoc
    0.70
     crochet
    0.64
    ratom
    0.64
     cryptocurrencies
    0.64
    earable
    0.62
     homebrew
    0.60
     alcoholic
    0.58
     metab
    0.56
     cryptocurrency
    0.56
     CoC
    0.56
    Activations Density 1.312%

    No Known Activations