© 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. 9-RES-JB
    11. 13699
    Prev
    Next
    INDEX
    Explanations

    words that are capitalized and start a new sentence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "And" or the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĨ
    -0.66
    pees
    -0.55
    1001
    -0.54
     nucleus
    -0.53
     ABE
    -0.51
     predominantly
    -0.51
     jumper
    -0.51
    sword
    -0.51
    olves
    -0.50
    ses
    -0.50
    POSITIVE LOGITS
    romeda
    1.75
    rea
    1.51
    ersen
    1.25
    hra
    1.22
    ré
    1.15
    rogens
    1.12
    alus
    1.09
     secondly
    1.09
    rew
    1.07
    uin
    1.06
    Activations Density 0.076%

    No Known Activations