© 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. 8-RES-JB
    11. 18551
    Prev
    Next
    INDEX
    Explanations

    phrases related to self-improvement and personal growth

    oai_token-act-pair · gpt-3.5-turbo

    statements and themes related to self-improvement and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reconstruction
    -0.61
     Bak
    -0.61
     )]
    -0.61
     Annex
    -0.59
    ilts
    -0.58
     Latest
    -0.56
    thodox
    -0.53
    ansky
    -0.53
    Intel
    -0.53
    Roy
    -0.53
    POSITIVE LOGITS
     yourself
    1.61
     yourselves
    1.36
     Yourself
    1.12
     your
    0.87
     YOUR
    0.80
     oneself
    0.78
    your
    0.71
    Your
    0.69
    poke
    0.68
    ichever
    0.66
    Activations Density 0.846%

    No Known Activations