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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9427
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions or perspectives

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and phrases that express personal viewpoints or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quished
    -0.90
    yip
    -0.78
     actionGroup
    -0.75
    TG
    -0.68
    rex
    -0.64
    bridge
    -0.64
    walk
    -0.63
    rift
    -0.63
    opausal
    -0.63
    untled
    -0.61
    POSITIVE LOGITS
     sense
    1.57
     terms
    1.31
     senses
    1.26
     terminology
    1.24
     nutshell
    1.21
     words
    1.19
     jargon
    1.19
     estimation
    1.19
     context
    1.10
     vein
    1.05
    Activations Density 0.138%

    No Known Activations