© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 4037
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or directives

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "we" indicating collective involvement or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    netflix
    -0.75
    nesota
    -0.69
     totality
    -0.64
    cum
    -0.64
    iment
    -0.63
     contradictions
    -0.62
    س
    -0.62
    lihood
    -0.62
    oubt
    -0.61
     Cord
    -0.61
    POSITIVE LOGITS
    've
    1.08
    'll
    1.02
    're
    0.99
    bsite
    0.97
    arily
    0.97
    athered
    0.91
    'd
    0.87
    eding
    0.85
    arers
    0.82
     apologise
    0.81
    Activations Density 0.241%

    No Known Activations