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. 18372
    Prev
    Next
    INDEX
    Explanations

    issues or problems related to different contexts or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    discussions surrounding social justice and accountability issues

    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
    asionally
    -0.60
    asma
    -0.60
    elta
    -0.56
    riend
    -0.55
     lug
    -0.54
     tossing
    -0.54
     sshd
    -0.53
     frantically
    -0.53
     litter
    -0.52
     slick
    -0.52
    POSITIVE LOGITS
     belongs
    1.23
     must
    1.19
     cannot
    1.17
     should
    1.14
     shall
    1.13
    must
    1.11
     ought
    1.10
     belonged
    1.08
     MUST
    1.06
     rests
    1.05
    Activations Density 0.421%

    No Known Activations