© 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. 20080
    Prev
    Next
    INDEX
    Explanations

    references to specific animals, such as dwarves, elephants, tigers, and monkeys

    oai_token-act-pair · gpt-3.5-turbo

    references to fantasy or mythical creatures, animals, and characters

    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
    nce
    -0.70
    aton
    -0.69
    549
    -0.69
    NC
    -0.69
    wise
    -0.68
    Asset
    -0.68
    IP
    -0.67
    ty
    -0.67
    lic
    -0.66
    York
    -0.66
    POSITIVE LOGITS
    aurus
    1.21
    hip
    1.17
    ervatives
    1.12
    mith
    1.06
    ongs
    1.04
    uggest
    1.01
    terday
    1.00
    paces
    1.00
    agascar
    0.99
    ettings
    0.97
    Activations Density 0.096%

    No Known Activations