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. 7-RES-JB
    6. 10516
    Prev
    Next
    INDEX
    Explanations

    terms related to knowledge and expertise

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge and understanding

    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
    ishable
    -0.63
    issions
    -0.63
    etheus
    -0.62
    redd
    -0.62
    atos
    -0.60
     Predator
    -0.60
     Devils
    -0.60
     earthqu
    -0.58
    itter
    -0.58
    odd
    -0.58
    POSITIVE LOGITS
    ledge
    1.19
    lege
    1.19
     glean
    0.92
    fulness
    0.90
    reading
    0.86
     comprehension
    0.85
    ledged
    0.85
    lessness
    0.77
     knowledge
    0.75
    liness
    0.74
    Activations Density 0.040%

    No Known Activations