© 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. 4064
    Prev
    Next
    INDEX
    Explanations

    the word "cage"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Cage" 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
    ]]
    -0.69
    utations
    -0.67
    nov
    -0.66
    iers
    -0.64
    ys
    -0.62
    agn
    -0.62
     init
    -0.62
    UD
    -0.61
     regist
    -0.61
     grad
    -0.61
    POSITIVE LOGITS
     Cage
    4.55
     cage
    1.84
     cages
    1.53
     Collider
    1.19
     Coil
    1.12
     Daredevil
    1.06
     Bane
    1.03
     Cyborg
    1.01
     Prison
    0.97
     Skywalker
    0.94
    Activations Density 0.018%

    No Known Activations