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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 20568
    Prev
    Next
    INDEX
    Explanations

    terms related to starting or initiating something, such as 'start', 'shot', 'upstart', and 'growth'

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to movement or progression

    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
    ancial
    -0.66
     pedigree
    -0.61
    aghan
    -0.61
    stock
    -0.60
    abre
    -0.60
     ping
    -0.59
    aley
    -0.56
    addock
    -0.55
     closest
    -0.55
    edin
    -0.55
    POSITIVE LOGITS
    xual
    1.05
    xia
    0.83
    ments
    0.81
    iances
    0.81
    ctr
    0.81
    iveness
    0.78
    enment
    0.76
    terday
    0.75
    ction
    0.73
    ment
    0.71
    Activations Density 0.077%

    No Known Activations