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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 7110
    Prev
    Next
    INDEX
    Explanations

    mentions of the researcher Emmanuel Stamatakis

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and references to specific people

    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
    icut
    -0.91
    icip
    -0.82
    ices
    -0.80
    eatures
    -0.79
    iasco
    -0.76
    icult
    -0.74
    scl
    -0.73
    culosis
    -0.73
    ioch
    -0.73
    inately
    -0.72
    POSITIVE LOGITS
    OPLE
    0.88
     Poles
    0.81
     Stam
    0.77
    atel
    0.67
    STR
    0.66
    ¯
    0.65
    ORTS
    0.65
    neum
    0.65
     Goodbye
    0.65
     Brav
    0.64
    Activations Density 0.028%

    No Known Activations