© 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. 11-RES-JB
    11. 22549
    Prev
    Next
    INDEX
    Explanations

    phrases related to adventure and exploration

    oai_token-act-pair · gpt-3.5-turbo

    elements related to fantasy and adventure narratives

    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
    Article
    -0.93
     GOODMAN
    -0.92
    tops
    -0.83
    blocks
    -0.81
    axies
    -0.79
    ontent
    -0.77
    Topics
    -0.75
    izont
    -0.73
    points
    -0.73
     Cheong
    -0.72
    POSITIVE LOGITS
     mysterious
    1.39
     supernatural
    1.36
     prophecy
    1.32
     demonic
    1.32
     sorce
    1.25
     mystical
    1.25
     sorcerer
    1.23
     cursed
    1.22
     magical
    1.20
     sinister
    1.17
    Activations Density 0.295%

    No Known Activations