© 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. 2-RES-JB
    11. 20814
    Prev
    Next
    INDEX
    Explanations

    phrases related to the founding of organizations or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to founders and their roles or significance

    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
    CDC
    -0.69
    mone
    -0.68
     reconc
    -0.67
    eely
    -0.61
    Ward
    -0.60
    asca
    -0.60
    ebin
    -0.59
     outpatient
    -0.59
    adal
    -0.58
    elaide
    -0.58
    POSITIVE LOGITS
     Founders
    1.12
    hip
    1.00
     Fathers
    0.97
    hips
    0.82
     founders
    0.79
    ervative
    0.77
    urus
    0.77
    emen
    0.72
    ãĥ³ãĤ¸
    0.71
     laureate
    0.70
    Activations Density 0.016%

    No Known Activations