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. 11-RES-JB
    6. 7350
    Prev
    Next
    INDEX
    Explanations

    adjectives with negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative or harsh descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ethics
    -0.67
    FU
    -0.64
    OTA
    -0.60
     Uganda
    -0.59
    ENE
    -0.58
     Matter
    -0.58
     RI
    -0.58
     MU
    -0.58
    ANS
    -0.57
    tions
    -0.56
    POSITIVE LOGITS
    uously
    1.22
    uous
    1.21
    ingly
    1.20
    htaking
    1.12
    igious
    1.04
    ctic
    1.01
    amental
    0.98
    acular
    0.96
    herent
    0.96
    uable
    0.96
    Activations Density 0.095%

    No Known Activations