© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3588
    Prev
    Next
    INDEX
    Explanations

    phrases related to heroic actions and gratitude

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to actions, responsibilities, and emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myself
    -0.56
     my
    -0.51
    ullivan
    -0.51
     mine
    -0.46
     MY
    -0.44
     My
    -0.43
    indal
    -0.42
     graded
    -0.42
     substrate
    -0.42
     referral
    -0.41
    POSITIVE LOGITS
     we
    1.55
    we
    1.40
    We
    1.33
     ourselves
    1.31
     We
    1.30
     WE
    1.13
     our
    1.07
    Our
    1.03
     us
    1.03
     ours
    0.95
    Activations Density 0.753%

    No Known Activations