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. 0-RES-JB
    6. 16181
    Prev
    Next
    INDEX
    Explanations

    references to newsletter subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of newsletters and related email sign-up contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itan
    -0.66
    Ĥ
    -0.66
     reverted
    -0.65
    imposed
    -0.64
    anc
    -0.64
    orthy
    -0.63
    Ī
    -0.60
    lit
    -0.60
    Ts
    -0.59
    nt
    -0.58
    POSITIVE LOGITS
     newsletter
    3.75
     Newsletter
    2.40
     newsletters
    2.34
     mailing
    1.52
    Newsletter
    1.51
     inbox
    1.24
     email
    1.22
     magazine
    1.19
     podcast
    1.19
     Emails
    1.17
    Activations Density 0.012%

    No Known Activations