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. 21865
    Prev
    Next
    INDEX
    Explanations

    acronyms starting with "CR"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Congressional Record (CR)

    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
     Idle
    -0.73
     following
    -0.65
     Na
    -0.65
     free
    -0.63
     Miko
    -0.63
     unused
    -0.61
     Vest
    -0.61
     Oath
    -0.61
     miss
    -0.60
     artific
    -0.60
    POSITIVE LOGITS
    CR
    3.43
    CP
    1.53
    CO
    1.50
    CL
    1.50
    BR
    1.50
    CS
    1.50
    TR
    1.49
    CD
    1.49
    PR
    1.48
    FR
    1.45
    Activations Density 0.015%

    No Known Activations