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. 15258
    Prev
    Next
    INDEX
    Explanations

    terms related to exams and testing

    oai_token-act-pair · gpt-3.5-turbo

    language related to examinations and assessments

    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
    taboola
    -0.76
    birds
    -0.71
    cedented
    -0.66
     slic
    -0.66
    gren
    -0.65
    tera
    -0.63
    spawn
    -0.62
     Kush
    -0.60
     wings
    -0.60
     Giant
    -0.60
    POSITIVE LOGITS
    iners
    1.11
     exams
    0.97
     exam
    0.96
    osterone
    0.94
     Exam
    0.93
     examinations
    0.93
     administered
    0.91
     examiner
    0.87
    icles
    0.83
    aminer
    0.80
    Activations Density 0.067%

    No Known Activations