Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6120
    Prev
    Next
    INDEX
    Explanations

    words related to organizational structures and entities

    oai_token-act-pair · gpt-3.5-turbo

    the word "Organ" and its variations 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
     submarine
    -0.78
    antage
    -0.71
    ww
    -0.71
     quirks
    -0.70
     downgrade
    -0.68
     preval
    -0.68
     recoil
    -0.68
     idle
    -0.67
    aults
    -0.67
     theorem
    -0.67
    POSITIVE LOGITS
     Organ
    4.12
    Organ
    3.00
    organ
    2.14
     organ
    1.93
     organizer
    1.70
     Organizations
    1.53
     organizers
    1.47
     organized
    1.41
    organized
    1.39
    GAN
    1.35
    Activations Density 0.025%

    No Known Activations