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. 6-RES-JB
    6. 23014
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize showcasing or presenting something

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements about capabilities or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sshd
    -0.76
    rontal
    -0.68
     Explan
    -0.65
     ado
    -0.65
    ipop
    -0.62
     extraction
    -0.62
    panel
    -0.62
     sugg
    -0.60
    finder
    -0.59
     gauge
    -0.59
    POSITIVE LOGITS
     absurdity
    0.80
     seriousness
    0.79
     versatility
    0.72
    true
    0.71
     dangers
    0.69
     enorm
    0.69
     indisp
    0.68
     importance
    0.67
    ibilities
    0.67
    ELF
    0.67
    Activations Density 0.460%

    No Known Activations