© 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. 3-RES-JB
    11. 22816
    Prev
    Next
    INDEX
    Explanations

    questions indicated by a question mark at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    questions or inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    athe
    -0.70
    riet
    -0.70
     encount
    -0.70
     yak
    -0.68
    kee
    -0.67
     soap
    -0.67
    aper
    -0.67
    apan
    -0.66
     worm
    -0.65
     marsh
    -0.64
    POSITIVE LOGITS
     Wouldn
    1.09
     Surely
    1.05
     Nope
    1.01
     Probably
    1.01
     Why
    0.99
     Perhaps
    0.99
     Certainly
    0.99
     Presumably
    0.97
     Maybe
    0.95
    ����
    0.93
    Activations Density 0.125%

    No Known Activations