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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11079
    Prev
    Next
    INDEX
    Explanations

    references to specific companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "at" followed by various numerical values representing positions or affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ceilings
    -0.71
    ratulations
    -0.69
    xual
    -0.67
    vous
    -0.65
    ministic
    -0.64
    Thumbnail
    -0.64
    material
    -0.64
    CLASS
    -0.64
    Console
    -0.63
     combatants
    -0.63
    POSITIVE LOGITS
     least
    1.00
     NYU
    0.93
     Goldman
    0.93
     Hew
    0.90
     UCLA
    0.90
     Baylor
    0.89
     Harvard
    0.88
     NASA
    0.88
    abase
    0.88
     Stanford
    0.88
    Activations Density 0.142%

    No Known Activations