Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7374
    Prev
    Next
    INDEX
    Explanations

    the word "Thor" along with associated contexts or mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Thor from mythology and comics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilies
    -0.74
    icals
    -0.73
    istas
    -0.71
    ello
    -0.68
    astery
    -0.67
     gardens
    -0.65
    esan
    -0.64
     caf
    -0.63
    ggies
    -0.63
     disp
    -0.62
    POSITIVE LOGITS
     Thor
    3.89
    Thor
    3.16
     thor
    1.89
     Loki
    1.72
     Asgard
    1.71
     Odin
    1.53
     Ragnarok
    1.39
     Ragnar
    1.38
     Hulk
    1.26
     Avengers
    1.26
    Activations Density 0.010%

    No Known Activations