© 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. 4411
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant impact or importance

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

    phrases that indicate significant roles or impacts

    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
    ©¶æ
    -0.76
    rehend
    -0.75
    mares
    -0.71
     Lust
    -0.69
    akis
    -0.68
    ð
    -0.66
    luaj
    -0.66
    ciating
    -0.65
    aturday
    -0.64
    cair
    -0.64
    POSITIVE LOGITS
     role
    1.62
     roles
    1.27
     part
    1.23
     pivotal
    1.21
    role
    1.13
     starring
    1.08
     vital
    1.04
     decisive
    1.02
     Role
    1.02
     integral
    1.02
    Activations Density 0.097%

    No Known Activations