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

    Neuronpedia

    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. 8-RES-JB
    11. 17586
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or plans attributed to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to plans, actions, and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.82
     Colomb
    -0.66
     paran
    -0.65
    omever
    -0.64
     poss
    -0.59
    Pros
    -0.59
    Russ
    -0.58
    Write
    -0.58
     oneself
    -0.57
    !.
    -0.57
    POSITIVE LOGITS
     consists
    0.96
     extends
    0.94
     relies
    0.90
     consisted
    0.89
     appears
    0.88
     illustrates
    0.87
     coincided
    0.86
     includes
    0.86
     continues
    0.86
     encompasses
    0.85
    Activations Density 0.302%

    No Known Activations