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. 10-RES-JB
    6. 17890
    Prev
    Next
    INDEX
    Explanations

    terms related to economic or monetary topics, specifically focused on gains or investments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to conditional statements and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mma
    -0.92
    rique
    -0.76
     Archer
    -0.74
     Archangel
    -0.73
    oland
    -0.69
     Parkinson
    -0.66
    venants
    -0.65
    ouched
    -0.64
     Choi
    -0.63
     anch
    -0.63
    POSITIVE LOGITS
     get
    1.57
    get
    1.56
     Get
    1.37
    Get
    1.33
    GET
    1.31
     Gets
    1.29
     GET
    1.27
     gotten
    1.27
     got
    1.26
     gets
    1.25
    Activations Density 0.139%

    No Known Activations