© 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. 6-RES-JB
    11. 14815
    Prev
    Next
    INDEX
    Explanations

    words related to broad abstract concepts or themes such as "world of fantasy" or "world of professional wrestling"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "the world of" followed by various subjects or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptoms
    -0.73
    sts
    -0.68
    */(
    -0.68
    aceous
    -0.66
     recite
    -0.65
     COUNTY
    -0.65
    aciously
    -0.65
    essee
    -0.63
    RM
    -0.62
    falls
    -0.61
    POSITIVE LOGITS
     ours
    0.70
     Warcraft
    0.67
     Atlantis
    0.67
     academia
    0.67
     Origin
    0.66
     Dreams
    0.65
    ESSION
    0.65
     sorts
    0.63
     superheroes
    0.63
     Grind
    0.63
    Activations Density 0.105%

    No Known Activations