© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 21524
    Prev
    Next
    INDEX
    Explanations

    pronouns and words related to personal reflection and self-identity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal identity and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /_
    -0.74
    cliffe
    -0.71
     "$:/
    -0.70
    ãĥ©ãĥ³
    -0.69
     âĢº
    -0.68
    20439
    -0.68
    earch
    -0.66
     Amin
    -0.65
     Azerbai
    -0.65
    ftime
    -0.64
    POSITIVE LOGITS
    'll
    0.84
     reluct
    0.79
     expended
    0.76
     blat
    0.76
     boarded
    0.76
    've
    0.74
    'd
    0.73
     wandered
    0.70
     sacrificed
    0.70
     drifted
    0.70
    Activations Density 1.364%

    No Known Activations