© 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. 6-RES-JB
    11. 10882
    Prev
    Next
    INDEX
    Explanations

    the concept of 'self' or self-related words and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to self-centeredness or self-interest

    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
     XIII
    -0.77
     GOODMAN
    -0.76
     Ashe
    -0.76
     Syndicate
    -0.75
     Nights
    -0.74
     Slay
    -0.71
     Vid
    -0.69
     Orchestra
    -0.67
     LAT
    -0.67
     Sierra
    -0.66
    POSITIVE LOGITS
    destruct
    1.26
     destruct
    1.04
     explanatory
    0.94
    conscious
    0.94
    same
    0.91
    upload
    0.87
    lessly
    0.84
    ridges
    0.84
     esteem
    0.80
    contained
    0.79
    Activations Density 0.024%

    No Known Activations