© 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 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. 11-RES-JB
    11. 14960
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "reality" in contexts related to TV or general situations

    oai_token-act-pair · gpt-3.5-turbo

    references to reality and its implications, particularly in the context of television

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    İĭ
    -0.75
    edo
    -0.73
    ucky
    -0.73
    ificantly
    -0.72
     anonym
    -0.72
    edin
    -0.71
    artney
    -0.71
    oyal
    -0.71
    intention
    -0.71
    tein
    -0.70
    POSITIVE LOGITS
     srfAttach
    0.89
     TV
    0.88
     tv
    0.86
     check
    0.85
    psons
    0.81
     television
    0.81
     distortion
    0.80
     Ens
    0.79
    ignment
    0.77
     Television
    0.77
    Activations Density 0.043%

    No Known Activations