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. 19517
    Prev
    Next
    INDEX
    Explanations

    acronyms related to political parties

    oai_token-act-pair · gpt-3.5-turbo

    references to political parties or movements

    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
    jer
    -0.72
     guiActiveUnfocused
    -0.68
     serv
    -0.68
     Forge
    -0.68
     chain
    -0.67
     salv
    -0.66
     boarding
    -0.64
     scrib
    -0.64
     haunted
    -0.63
     relay
    -0.62
    POSITIVE LOGITS
    PP
    4.33
     PP
    1.92
    PT
    1.61
    CP
    1.56
    PN
    1.53
    MP
    1.48
    NP
    1.46
    DP
    1.45
    PD
    1.42
    FP
    1.41
    Activations Density 0.010%

    No Known Activations