© 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. 3202
    Prev
    Next
    INDEX
    Explanations

    words related to social organization and structures, particularly around group behavior and control

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

    words related to materials or substance degradation

    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
     delay
    -0.76
     FIRST
    -0.60
     overlook
    -0.59
     late
    -0.57
     logger
    -0.56
     hiatus
    -0.56
     raft
    -0.56
     Tick
    -0.56
     muse
    -0.55
     scratch
    -0.55
    POSITIVE LOGITS
    vals
    1.13
    quez
    1.12
    zona
    1.12
    quet
    1.08
    zzi
    1.04
    archy
    1.02
    ques
    1.01
    zzle
    1.00
    ving
    0.98
    yet
    0.97
    Activations Density 0.029%

    No Known Activations