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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 9753
    Prev
    Next
    INDEX
    Explanations

    words related to success or failure, often associated with intense emotions, such as "victory," "devastating blow," "betrayal," and "shift."

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with conflict, setbacks, and victories in discussions or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Known
    -0.69
    rooms
    -0.68
     Tables
    -0.68
     warehouses
    -0.68
     branches
    -0.67
    ancies
    -0.67
    properties
    -0.66
     Elements
    -0.66
     hotels
    -0.63
     Sections
    -0.63
    POSITIVE LOGITS
     deterrent
    0.81
    BACK
    0.74
     departure
    0.73
     akin
    0.72
    brainer
    0.72
    ozy
    0.71
     tactic
    0.71
    atform
    0.71
     reversal
    0.70
     testament
    0.69
    Activations Density 0.359%

    No Known Activations