© 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. 10-RES-JB
    11. 20279
    Prev
    Next
    INDEX
    Explanations

    mentions of board members and boards

    oai_token-act-pair · gpt-3.5-turbo

    references to boards and their members

    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
    sson
    -0.71
    udeau
    -0.69
    olson
    -0.66
    çīĪ
    -0.62
     IMAGES
    -0.62
     Chau
    -0.61
     Jude
    -0.61
     adul
    -0.61
     Bieber
    -0.61
     foil
    -0.60
    POSITIVE LOGITS
    walk
    1.39
    room
    1.29
    rooms
    1.18
    members
    1.17
    member
    1.14
    chair
    1.06
    chairs
    1.02
     trustees
    1.02
     members
    1.01
     member
    1.00
    Activations Density 0.032%

    No Known Activations