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. 5910
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, particularly years of relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time and relationships

    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
     standalone
    -0.63
     VIDEOS
    -0.61
     gaps
    -0.59
     casualty
    -0.56
     hurdle
    -0.54
    ãĥ¥
    -0.54
    Adapt
    -0.54
    Psy
    -0.54
     DEA
    -0.53
     backdoor
    -0.53
    POSITIVE LOGITS
     fame
    1.06
    votes
    0.74
    EStreamFrame
    0.71
    ;;;;;;;;;;;;
    0.71
    ulhu
    0.69
    isine
    0.69
     persuasion
    0.67
    yrus
    0.66
    rand
    0.66
    gone
    0.64
    Activations Density 0.750%

    No Known Activations