© 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. 14879
    Prev
    Next
    INDEX
    Explanations

    instances where something is carefully examined or analyzed

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scrutiny and examination

    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
    galitarian
    -0.74
    cember
    -0.71
    ADRA
    -0.71
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.70
    hyde
    -0.69
    Effective
    -0.68
    Acknowled
    -0.68
    FORE
    -0.67
    OURCE
    -0.66
    ministic
    -0.65
    POSITIVE LOGITS
    acles
    0.95
    acular
    0.91
    ographs
    0.89
    ocular
    0.87
    icles
    0.86
    opol
    0.86
    icularly
    0.86
    etary
    0.82
    entimes
    0.81
    ition
    0.80
    Activations Density 0.018%

    No Known Activations