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

    Neuronpedia

    APICircuit 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. 19558
    Prev
    Next
    INDEX
    Explanations

    the term "free"

    oai_token-act-pair · gpt-3.5-turbo

    words related to freedom

    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
     Everywhere
    -0.82
     Hale
    -0.73
     Conrad
    -0.70
     Harrington
    -0.70
     Authority
    -0.69
     Io
    -0.69
    ç¥ŀ
    -0.66
     Shogun
    -0.65
     Transcript
    -0.65
     Ancients
    -0.64
    POSITIVE LOGITS
    eware
    1.05
    bies
    1.03
    estyle
    1.02
    ety
    1.00
    aling
    0.97
    ighter
    0.97
    eworld
    0.96
    eways
    0.96
    etime
    0.95
    aky
    0.94
    Activations Density 0.022%

    No Known Activations