© 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. 15646
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by expressions indicating uncertainty or conversational language

    oai_token-act-pair · gpt-3.5-turbo

    expressions that emphasize personal involvement or awareness in a conversation

    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
     srfAttach
    -0.62
    ournals
    -0.62
    izon
    -0.61
     sunset
    -0.57
    iors
    -0.57
    ĸļ
    -0.57
    iesta
    -0.56
    yss
    -0.55
    emonium
    -0.55
     ARTICLE
    -0.55
    POSITIVE LOGITS
     guessed
    1.06
     dunno
    0.96
     know
    0.82
     paraph
    0.80
     guess
    0.79
     presume
    0.78
     suppose
    0.77
     say
    0.76
     believe
    0.74
     mean
    0.70
    Activations Density 0.150%

    No Known Activations