© 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. 10196
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by a verb or a possessive pronoun

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating people's perceptions and actions towards needs and wants

    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
     Forth
    -0.76
     Reloaded
    -0.76
     Grav
    -0.70
     Cla
    -0.66
     Slim
    -0.63
     Marine
    -0.62
     Hast
    -0.61
     Brigade
    -0.61
     ripple
    -0.59
     Pace
    -0.59
    POSITIVE LOGITS
     deems
    1.10
     deem
    0.97
     dislike
    0.96
     otherwise
    0.95
     loved
    0.93
     perceive
    0.92
     disliked
    0.86
     already
    0.84
     previously
    0.82
     deemed
    0.82
    Activations Density 0.223%

    No Known Activations