© 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. 10-RES-JB
    11. 3080
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "kind" followed by a numeral

    oai_token-act-pair · gpt-3.5-turbo

    expressions that convey uncertainty or vagueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Membership
    -0.64
     Surveillance
    -0.58
     Expansion
    -0.58
     Vend
    -0.54
     Milan
    -0.54
    ulia
    -0.53
    OPE
    -0.53
    INST
    -0.53
     Abbey
    -0.52
     Mobile
    -0.52
    POSITIVE LOGITS
    nered
    0.91
     of
    0.86
    ling
    0.85
    lier
    0.85
    of
    0.85
    hearted
    0.84
    heartedly
    0.84
     thereof
    0.83
    lined
    0.81
    entimes
    0.79
    Activations Density 0.030%

    No Known Activations