© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 3142
    Prev
    Next
    INDEX
    Explanations

    names of animals

    oai_token-act-pair · gpt-3.5-turbo

    names of animals or characters in titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orship
    -0.73
     AFP
    -0.71
    ancies
    -0.71
     avail
    -0.67
     franc
    -0.67
     aloud
    -0.66
     isol
    -0.66
     impart
    -0.66
    icably
    -0.65
    ervation
    -0.64
    POSITIVE LOGITS
     Tail
    1.10
     Squad
    1.07
    Nation
    1.06
     Tracks
    1.06
     Nation
    1.04
     Claw
    1.02
     Creek
    1.02
    Girl
    1.01
    Mania
    0.98
     Soup
    0.97
    Activations Density 0.135%

    No Known Activations