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. 7950
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic papers or articles for some special issues or important topics for discussion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "on" referring to topics of discussion

    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
    SourceFile
    -0.72
    ptives
    -0.70
    waters
    -0.68
    acies
    -0.65
    ring
    -0.65
    externalActionCode
    -0.65
    Fans
    -0.64
    à©
    -0.63
    TY
    -0.62
    ACT
    -0.62
    POSITIVE LOGITS
     behalf
    1.54
    eday
    1.01
    erous
    0.96
    yx
    0.87
    eworld
    0.81
    etime
    0.80
    shore
    0.80
     Monday
    0.80
     Demand
    0.78
    site
    0.76
    Activations Density 0.161%

    No Known Activations