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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9923
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a binary decision or a choice between two possibilities

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating uncertainty or indecision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪ
    -0.71
    ĸļ
    -0.69
     Rooms
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    äºĶ
    -0.66
    083
    -0.65
    ¿
    -0.65
    ãĥķãĤ©
    -0.65
    SourceFile
    -0.65
     srfAttach
    -0.62
    POSITIVE LOGITS
     technically
    0.84
     existed
    0.81
     swayed
    0.77
     qualifies
    0.77
    theless
    0.76
     mete
    0.72
     necessarily
    0.71
     they
    0.71
     qualified
    0.69
    igham
    0.68
    Activations Density 0.018%

    No Known Activations