© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 17113
    Prev
    Next
    INDEX
    Explanations

    references to the Memphis Grizzlies basketball team

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Memphis Grizzlies basketball team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lying
    -0.84
    ship
    -0.75
    oward
    -0.75
    wealth
    -0.73
    spring
    -0.72
    boarding
    -0.70
    sworth
    -0.70
    hood
    -0.70
    âĵĺ
    -0.68
    ded
    -0.68
    POSITIVE LOGITS
    phis
    1.23
     Grizzlies
    1.23
    essee
    0.85
    cano
    0.78
    ascus
    0.78
     Memphis
    0.74
     mosqu
    0.70
    mma
    0.70
     eleph
    0.70
     Chains
    0.69
    Activations Density 0.009%

    No Known Activations