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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2102
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by questions or statements expressing doubt, uncertainty, or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating personal involvement or address in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.75
    ãĤ¦ãĤ¹
    -0.72
    ãĥĵ
    -0.70
    uces
    -0.70
     Giul
    -0.66
     srfAttach
    -0.66
     Conversation
    -0.65
     Integrity
    -0.64
    ufact
    -0.64
    opens
    -0.64
    POSITIVE LOGITS
     deserve
    1.09
     intend
    1.08
     recognise
    1.01
     lose
    0.99
     need
    0.99
     propose
    0.97
     owe
    0.97
     think
    0.95
     mean
    0.95
     expect
    0.95
    Activations Density 0.079%

    No Known Activations