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. 9-RES-JB
    6. 11072
    Prev
    Next
    INDEX
    Explanations

    the word "ob"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "ob"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivities
    -0.85
    imates
    -0.74
    yards
    -0.69
     cort
    -0.67
     Orient
    -0.66
    ³³³³³³³³
    -0.65
    Angelo
    -0.62
     ORIG
    -0.62
     Painter
    -0.62
     Divinity
    -0.62
    POSITIVE LOGITS
    acter
    1.22
    server
    1.18
    edient
    1.17
    lique
    1.14
    edience
    1.14
    acco
    1.12
    rien
    1.09
    bing
    1.08
    livion
    1.07
    fusc
    1.06
    Activations Density 0.032%

    No Known Activations