Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20104
    Prev
    Next
    INDEX
    Explanations

    terms related to financial aspects, specifically mentioning funding and capital

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with funding, violence, and movement in various contexts

    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
    ovie
    -0.69
    cise
    -0.67
    ammad
    -0.64
    orah
    -0.63
    ITNESS
    -0.63
    endment
    -0.61
    purpose
    -0.59
    CHA
    -0.59
     Saying
    -0.59
     ______
    -0.58
    POSITIVE LOGITS
     tends
    1.34
     dominates
    1.27
     dictates
    1.25
     continues
    1.21
     occurs
    1.18
     slows
    1.16
     varies
    1.16
     exists
    1.15
     prevailed
    1.15
     persists
    1.14
    Activations Density 0.339%

    No Known Activations