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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6258
    Prev
    Next
    INDEX
    Explanations

    descriptions of mythical creatures and monsters

    oai_token-act-pair · gpt-3.5-turbo

    references to mythical and extraterrestrial creatures

    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
    Recommend
    -0.77
     Playoff
    -0.76
     Coverage
    -0.71
     Values
    -0.71
    ourt
    -0.71
     Recommend
    -0.69
     Playoffs
    -0.68
    illet
    -0.67
    Effective
    -0.66
    arten
    -0.66
    POSITIVE LOGITS
     humanoid
    1.28
     inhab
    1.16
     Cthulhu
    1.11
     lurking
    1.09
     menace
    1.05
     invading
    1.04
     beings
    1.03
     invaders
    1.02
     UFOs
    1.02
     lair
    1.02
    Activations Density 0.592%

    No Known Activations