© 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. 4029
    Prev
    Next
    INDEX
    Explanations

    technical terms related to competitions or events

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

    instances of the word "there" in various contexts

    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
    OWS
    -0.59
     consistent
    -0.55
     Alley
    -0.53
     captivity
    -0.53
    ORE
    -0.52
    å°Ĩ
    -0.52
     CO
    -0.52
     fearless
    -0.52
     Penny
    -0.52
    Merc
    -0.51
    POSITIVE LOGITS
    ndum
    1.31
    nc
    1.16
    nda
    1.07
    lict
    1.07
    avement
    1.05
    liction
    1.04
    cht
    1.03
    phthal
    1.02
    choes
    1.02
    tz
    1.00
    Activations Density 0.057%

    No Known Activations