© 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. 1-RES-JB
    11. 20138
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific fictional characters or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to "Giant" and "Killer" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    earchers
    -0.86
    gettable
    -0.85
    skirts
    -0.82
    etsk
    -0.81
    unts
    -0.79
    metic
    -0.78
    chel
    -0.78
    attled
    -0.76
    atche
    -0.76
    testers
    -0.75
    POSITIVE LOGITS
     Giant
    1.22
     Killer
    0.91
     Panda
    0.88
     Dome
    0.84
     Beasts
    0.83
     Breaker
    0.83
     Prix
    0.83
     Toad
    0.83
     Slayer
    0.82
     Insect
    0.82
    Activations Density 0.013%

    No Known Activations