© 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. 2-RES-JB
    11. 17750
    Prev
    Next
    INDEX
    Explanations

    references to a specific platform called "Hub" and different versions of it

    oai_token-act-pair · gpt-3.5-turbo

    references to "Hub" or related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -1.00
    anguage
    -0.87
    terday
    -0.84
    DonaldTrump
    -0.75
    teenth
    -0.72
    uary
    -0.71
    ãģį
    -0.70
     FORM
    -0.69
    NetMessage
    -0.69
    esthetic
    -0.68
    POSITIVE LOGITS
    hub
    1.29
    Hub
    1.23
     Hub
    1.23
    bub
    1.15
    bard
    1.11
    rod
    1.01
    staff
    1.01
    lot
    0.97
    bies
    0.94
    master
    0.92
    Activations Density 0.011%

    No Known Activations