Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 17415
    Prev
    Next
    INDEX
    Explanations

    verbs like 'can', 'hear', 'purchase', 'expect', 'see', 'take', 'fully', 'use', indicating capabilities or actions

    oai_token-act-pair · gpt-3.5-turbo

    words indicating capability or possibility

    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
     Haf
    -0.63
    eva
    -0.61
     Axel
    -0.59
     Passive
    -0.58
     Eli
    -0.57
     Metatron
    -0.57
    scripts
    -0.56
     Skinner
    -0.56
     Goodell
    -0.56
     Dud
    -0.55
    POSITIVE LOGITS
     deem
    0.90
     dearly
    0.84
     deems
    0.81
     frequ
    0.78
    abouts
    0.78
    ģĸ
    0.77
     encounter
    0.76
     sorely
    0.76
    968
    0.75
     "$:/
    0.75
    Activations Density 0.244%

    No Known Activations