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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 17329
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial and economic activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and public policy

    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
    é¾įå
    -0.68
    ãĥ´
    -0.63
    ãĤ¤ãĥĪ
    -0.63
    ãĥĥãĥī
    -0.62
    çĭ
    -0.58
    âķIJ
    -0.57
    å¯
    -0.57
    ãĤ¯
    -0.56
    ä½
    -0.56
    SN
    -0.55
    POSITIVE LOGITS
     Copyright
    0.52
    ioxide
    0.50
    iage
    0.49
    ¶
    0.49
    ratulations
    0.45
    enko
    0.44
     âĢº
    0.43
     optimization
    0.43
    ancies
    0.42
     resume
    0.41
    Activations Density 0.501%

    No Known Activations