© 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. 7-RES-JB
    11. 21374
    Prev
    Next
    INDEX
    Explanations

    descriptions of size, particularly emphasizing largeness

    oai_token-act-pair · gpt-3.5-turbo

    terms describing size or magnitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Theme
    -0.80
     Assass
    -0.77
    anwhile
    -0.75
    ä¸Ĭ
    -0.74
    WP
    -0.74
    âķIJâķIJ
    -0.73
    actionDate
    -0.71
    funding
    -0.71
    neg
    -0.70
    beat
    -0.70
    POSITIVE LOGITS
     sized
    1.26
     diameter
    1.16
     intestine
    1.05
     rectangular
    1.01
     bulky
    1.01
     cyl
    1.01
     stature
    1.00
     size
    0.98
     sizes
    0.95
     spherical
    0.95
    Activations Density 0.092%

    No Known Activations