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. 10-RES-JB
    6. 1950
    Prev
    Next
    INDEX
    Explanations

    webpage-related text for permissions and reprints

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to copyright and publication permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebin
    -0.68
    naire
    -0.67
    fy
    -0.66
    estern
    -0.64
    watching
    -0.63
    llah
    -0.63
    okemon
    -0.62
    swer
    -0.62
     awaits
    -0.61
    zees
    -0.61
    POSITIVE LOGITS
     reprint
    1.10
     license
    1.01
     licensing
    0.98
    license
    0.93
     permission
    0.85
    Lic
    0.84
     licence
    0.80
     permissions
    0.79
     licens
    0.77
     prohibition
    0.77
    Activations Density 0.049%

    No Known Activations