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. 6-RES-JB
    6. 5981
    Prev
    Next
    INDEX
    Explanations

    terms related to attributes or qualities such as being "ridden", "grade", "based", "sponsored", "smelling", "owned", "free", "long", "winning", "negative", "positive", "propelled", "grade", "negative", "propelled", "

    oai_token-act-pair · gpt-3.5-turbo

    terms related to business and organizational operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elcome
    -0.80
    veyard
    -0.77
    hner
    -0.74
    ÄŁ
    -0.74
    conn
    -0.73
    gotten
    -0.72
     Downs
    -0.71
    Arm
    -0.70
     Clause
    -0.69
    idelines
    -0.69
    POSITIVE LOGITS
     olds
    0.87
     entertainment
    0.74
     guest
    0.70
     event
    0.70
     enterprise
    0.69
     ones
    0.68
     super
    0.68
    itiz
    0.68
     educational
    0.67
    rency
    0.67
    Activations Density 0.303%

    No Known Activations