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. 4-RES-JB
    6. 3927
    Prev
    Next
    INDEX
    Explanations

    words related to criticism or disapproval, particularly strong rebukes or rejections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reb" in various contexts

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

    No Comments

    Negative Logits
    lihood
    -0.80
     Kafka
    -0.77
    âĢ¢âĢ¢
    -0.68
     Grail
    -0.67
     Valhalla
    -0.67
     Corpus
    -0.67
     Halls
    -0.66
    teness
    -0.65
     Nost
    -0.64
     Lap
    -0.64
    POSITIVE LOGITS
    ounding
    1.17
    ounded
    1.06
    uffed
    1.01
    anche
    0.99
    uked
    0.94
    uls
    0.94
    elling
    0.92
    aul
    0.92
    elled
    0.92
    ukes
    0.89
    Activations Density 0.008%

    No Known Activations