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. 7-RES-JB
    6. 15132
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences indicating the target or purpose of an action

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the word "aimed at" indicating intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anon
    -0.76
     Warrant
    -0.69
    wine
    -0.68
    colour
    -0.66
    check
    -0.66
    amide
    -0.64
    minus
    -0.64
    ABLE
    -0.64
    clip
    -0.63
    plugins
    -0.62
    POSITIVE LOGITS
     preserving
    1.07
     maximizing
    1.07
     solving
    1.07
     preventing
    1.05
     improving
    1.04
     achieving
    1.01
     combating
    1.00
     avoiding
    0.99
     ensuring
    0.98
     reducing
    0.95
    Activations Density 0.053%

    No Known Activations