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. 9925
    Prev
    Next
    INDEX
    Explanations

    phrases related to directing or channeling resources or efforts towards a specific goal or destination

    oai_token-act-pair · gpt-3.5-turbo

    terms related to business processes or conversion paths

    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
    Dur
    -0.77
    lihood
    -0.72
    DonaldTrump
    -0.71
    Rated
    -0.69
    Extreme
    -0.67
    mob
    -0.64
     Ath
    -0.64
     losers
    -0.62
     Proud
    -0.58
     IST
    -0.57
    POSITIVE LOGITS
    nels
    1.20
     funnel
    1.13
    eering
    0.99
    odynamic
    0.97
    glers
    0.93
    nel
    0.93
    ming
    0.88
    odynam
    0.85
    nell
    0.82
    abwe
    0.82
    Activations Density 0.027%

    No Known Activations