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. 16154
    Prev
    Next
    INDEX
    Explanations

    economic and strategic terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economics and strategic decision-making

    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
    lihood
    -0.79
     Aber
    -0.70
     Dome
    -0.70
     Virgin
    -0.68
     Tune
    -0.68
     Maid
    -0.67
     DRAG
    -0.66
     Feast
    -0.66
     thence
    -0.66
     Kimber
    -0.65
    POSITIVE LOGITS
    ists
    1.60
    istics
    1.35
    ist
    1.35
    istic
    1.31
    ues
    1.31
    istical
    1.30
    istically
    1.30
    ical
    1.28
    uers
    1.22
    ics
    1.21
    Activations Density 0.050%

    No Known Activations