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. 5569
    Prev
    Next
    INDEX
    Explanations

    the word "able" followed by a verb, indicating capability or possibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the ability or capacity to do something

    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
     Parents
    -0.62
     Tradition
    -0.61
    email
    -0.60
     Technique
    -0.60
     Emanuel
    -0.57
     sterling
    -0.57
    edient
    -0.56
     Clemson
    -0.55
     germ
    -0.55
    aternity
    -0.55
    POSITIVE LOGITS
    bodied
    1.06
    ioned
    0.96
    't
    0.87
    reys
    0.78
     access
    0.77
     bod
    0.75
    ny
    0.75
    ittees
    0.73
     Pradesh
    0.72
     afford
    0.72
    Activations Density 0.040%

    No Known Activations