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. 3967
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to current events and politics

    oai_token-act-pair · gpt-3.5-turbo

    references to significant political entities and events

    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
    tnc
    -0.80
    EStreamFrame
    -0.68
     guiActiveUnfocused
    -0.67
    î
    -0.64
     behalf
    -0.63
     externalToEVAOnly
    -0.61
    nants
    -0.59
    COMPLE
    -0.59
    7601
    -0.58
    ãģĨ
    -0.57
    POSITIVE LOGITS
     meanwhile
    0.80
     thri
    0.69
     isn
    0.68
     crept
    0.67
     Slate
    0.66
     reacted
    0.65
     analogy
    0.65
     sucks
    0.65
     hasn
    0.65
     grew
    0.65
    Activations Density 0.864%

    No Known Activations