© 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. 2559
    Prev
    Next
    INDEX
    Explanations

    phrases related to speculative or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases that imply hypothetical scenarios

    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
    idates
    -0.72
    throp
    -0.67
     Towns
    -0.62
    aires
    -0.60
    roxy
    -0.60
     Fraz
    -0.59
     Airl
    -0.58
     rebound
    -0.57
     vendors
    -0.55
     couples
    -0.54
    POSITIVE LOGITS
     magically
    0.80
    Ãł
    0.76
    rael
    0.74
     somehow
    0.71
     invincible
    0.65
    è£ħ
    0.65
     superhuman
    0.64
    paste
    0.64
     SECTION
    0.64
    itting
    0.63
    Activations Density 0.186%

    No Known Activations