Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 448
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive pronouns indicating ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusion or companionship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partName
    -0.67
    ãĥĭ
    -0.64
    otine
    -0.63
     Pai
    -0.62
    pmwiki
    -0.62
    +)
    -0.59
     Heist
    -0.58
    1080
    -0.57
     probabilities
    -0.56
    cture
    -0.56
    POSITIVE LOGITS
    atic
    0.96
    atics
    0.77
    andering
    0.72
    stretched
    0.68
    ngth
    0.67
    hei
    0.66
    ghan
    0.65
     mates
    0.65
    alian
    0.65
    lain
    0.63
    Activations Density 0.122%

    No Known Activations