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. 7095
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or tasks being accomplished

    oai_token-act-pair · gpt-3.5-turbo

    expressions of communal activity and collaboration

    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
    ONSORED
    -0.65
    Attach
    -0.59
    ISION
    -0.58
     circumstances
    -0.56
     Accountability
    -0.56
     Integrity
    -0.56
     Justice
    -0.55
    ãĥĦ
    -0.55
     Audit
    -0.54
     reforms
    -0.54
    POSITIVE LOGITS
    joice
    0.71
    wolves
    0.68
    unts
    0.67
    their
    0.65
    tumblr
    0.62
    animate
    0.62
    ometimes
    0.62
    they
    0.62
     cones
    0.61
    common
    0.60
    Activations Density 1.890%

    No Known Activations