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. 16762
    Prev
    Next
    INDEX
    Explanations

    pronouns 'you', 'I', and 'we' when used together with others

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    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
    actionDate
    -0.74
    etting
    -0.68
    Deal
    -0.66
    nec
    -0.64
    vernment
    -0.64
    forestation
    -0.64
    umo
    -0.64
    Installation
    -0.63
     WARN
    -0.62
    .–
    -0.62
    POSITIVE LOGITS
     others
    0.94
    rogen
    0.90
     vice
    0.80
     consequently
    0.80
    rogens
    0.80
     therefore
    0.76
     Sons
    0.72
     other
    0.70
     secondly
    0.70
     mates
    0.70
    Activations Density 0.116%

    No Known Activations