© 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. 23465
    Prev
    Next
    INDEX
    Explanations

    phrases related to superheroes and comic book characters, especially those related to the X-Men

    oai_token-act-pair · gpt-3.5-turbo

    references to the "X-Men" franchise

    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
    ufact
    -0.69
     EntityItem
    -0.69
     Cla
    -0.67
     TODAY
    -0.67
    ieri
    -0.66
     digestion
    -0.66
     ado
    -0.65
     msec
    -0.65
     Suc
    -0.65
     quitting
    -0.62
    POSITIVE LOGITS
    shaped
    1.07
    rays
    1.00
    factor
    0.93
    sized
    0.91
    Factor
    0.91
    Ray
    0.90
    ray
    0.89
    level
    0.89
    series
    0.89
    coord
    0.89
    Activations Density 0.039%

    No Known Activations