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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 447
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" used to connect phrases

    oai_token-act-pair · gpt-4-turbo

    phrases related to authority figures or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :(
    -0.71
    :[
    -0.68
    éŃĶ
    -0.66
    è»
    -0.65
    itans
    -0.64
    odcast
    -0.62
    hov
    -0.62
    CRIP
    -0.62
    ":""},{"
    -0.62
    IRT
    -0.58
    POSITIVE LOGITS
     consequently
    1.11
     therefore
    1.08
     hence
    1.03
     thus
    1.01
    rogens
    0.96
     possibly
    0.93
     then
    0.93
     thereby
    0.93
    rogen
    0.93
    romeda
    0.89
    Activations Density 0.931%

    No Known Activations