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. 9-RES-JB
    6. 10610
    Prev
    Next
    INDEX
    Explanations

    names and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    email addresses and personal names

    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
     Disorder
    -1.07
     Accuracy
    -1.03
     Society
    -1.01
     Desk
    -1.00
     Inspection
    -0.99
     Index
    -0.99
     Movement
    -0.98
     Reconstruction
    -0.97
     Humanity
    -0.97
     Units
    -0.96
    POSITIVE LOGITS
    john
    1.34
    olson
    1.18
    brown
    1.16
    maxwell
    1.15
    clinton
    1.14
    kefeller
    1.09
    izabeth
    1.08
    @
    1.05
    1981
    1.05
    mc
    1.04
    Activations Density 0.155%

    No Known Activations