© 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. 6-RES-JB
    11. 11728
    Prev
    Next
    INDEX
    Explanations

    first-person statements expressing personal thoughts or actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal reflection and subjective opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conformity
    -0.58
     harms
    -0.55
    MpServer
    -0.53
     delinqu
    -0.51
    forms
    -0.51
     deeds
    -0.50
     subsistence
    -0.49
     Klux
    -0.49
     vitality
    -0.49
     Samar
    -0.48
    POSITIVE LOGITS
     recommend
    0.65
     curious
    0.62
     delve
    0.61
     appreciate
    0.60
    uno
    0.59
     imagine
    0.59
     fond
    0.59
     admittedly
    0.57
     wondered
    0.57
     wondering
    0.56
    Activations Density 0.840%

    No Known Activations