© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 22957
    Prev
    Next
    INDEX
    Explanations

    keywords related to central themes or key elements around which a situation or concept revolves

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to actions and processes that revolve around a central theme

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ee
    -0.71
    apon
    -0.67
    ingham
    -0.64
    ifts
    -0.64
     blindness
    -0.62
    liam
    -0.62
    rade
    -0.61
    itcher
    -0.59
    Miller
    -0.59
    ipping
    -0.58
    POSITIVE LOGITS
     revolves
    1.49
     revolving
    0.82
     centered
    0.81
     nutshell
    0.80
     boils
    0.78
     principally
    0.77
    pins
    0.77
    ĸļ
    0.74
    sect
    0.72
    SHIP
    0.72
    Activations Density 0.015%

    No Known Activations