© 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. 7-RES-JB
    11. 17088
    Prev
    Next
    INDEX
    Explanations

    phrases related to mythical creatures or fantasy scenarios, particularly those involving magical beings like dragons or elemental forces

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thumbnail
    -0.76
    OUGH
    -0.70
    ship
    -0.67
    OWS
    -0.61
     MFT
    -0.59
    Submit
    -0.58
    ships
    -0.58
    STE
    -0.57
     Squid
    -0.56
    OVER
    -0.55
    POSITIVE LOGITS
    aurus
    1.29
    ync
    1.12
    ylum
    1.10
    utra
    1.09
    quez
    1.09
    daq
    1.08
    cius
    1.05
    leep
    1.04
    peed
    1.01
    pect
    1.01
    Activations Density 0.053%

    No Known Activations