© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4388
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or state with specific preceding context, such as 'sitting on', 'receiving', 'serving in'

    oai_token-act-pair · gpt-3.5-turbo

    gerund forms of verbs indicating active or repetitive actions

    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
    pg
    -0.79
    twitch
    -0.67
    vu
    -0.63
    ère
    -0.63
    inho
    -0.61
    atell
    -0.60
     translating
    -0.60
     translation
    -0.60
    DragonMagazine
    -0.60
    ogy
    -0.59
    POSITIVE LOGITS
    redients
    0.79
    ãĤ¢ãĥ«
    0.72
     Cobra
    0.63
    itially
    0.62
     constituents
    0.62
     engagements
    0.61
     oneself
    0.60
    phas
    0.60
     Rebell
    0.58
     Pengu
    0.57
    Activations Density 0.135%

    No Known Activations