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. 11-RES-JB
    6. 15490
    Prev
    Next
    INDEX
    Explanations

    words related to specific characters or terms such as 'Amiibo'

    oai_token-act-pair · gpt-3.5-turbo

    personal pronouns and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.66
    é»Ĵ
    -0.61
     Sloven
    -0.61
     Malfoy
    -0.58
     habit
    -0.57
     boundaries
    -0.55
    advertisement
    -0.54
     Romania
    -0.54
     wit
    -0.54
     elig
    -0.54
    POSITIVE LOGITS
    assador
    1.11
    rican
    1.00
    akeru
    0.94
    ICAN
    0.92
    ibo
    0.91
    cade
    0.89
    anwhile
    0.89
    uments
    0.84
    ixture
    0.83
    athering
    0.81
    Activations Density 0.105%

    No Known Activations