© 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. 9-RES-JB
    11. 15747
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "I think" or "I see"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gutenberg
    -0.65
     Hels
    -0.65
     Occupations
    -0.64
     delinquent
    -0.64
    ĸļ
    -0.64
     Reborn
    -0.63
    upon
    -0.62
     TMZ
    -0.59
     alias
    -0.59
     passers
    -0.59
    POSITIVE LOGITS
     think
    1.10
    rene
    1.01
     personally
    0.98
     believe
    0.92
     optimistic
    0.90
     hope
    0.87
     guess
    0.87
     worry
    0.86
     advise
    0.86
     doubt
    0.86
    Activations Density 0.335%

    No Known Activations