© 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. 0-RES-JB
    11. 2692
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Batman"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Bat" in various contexts

    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
    earch
    -0.80
    fff
    -0.70
    imity
    -0.67
    ormon
    -0.63
    ensional
    -0.62
    oin
    -0.62
    eki
    -0.62
    ocrates
    -0.62
    INESS
    -0.62
    phia
    -0.61
    POSITIVE LOGITS
     Bat
    3.88
    Bat
    3.09
     bat
    1.89
    bat
    1.84
     BAT
    1.54
    BAT
    1.50
    bats
    1.40
     bats
    1.39
     Batman
    1.38
    Batman
    1.33
    Activations Density 0.006%

    No Known Activations