© 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. 10-RES-JB
    11. 17318
    Prev
    Next
    INDEX
    Explanations

    motivational phrases or reflections

    oai_token-act-pair · gpt-3.5-turbo

    motivational statements and themes related to personal growth and life purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —"
    -1.11
    "—
    -0.80
    âĶĢ
    -0.79
    ãĥīãĥ©
    -0.76
    Enlarge
    -0.74
    )—
    -0.74
    —
    -0.73
    ,[
    -0.72
     ÂŃ
    -0.69
    Å«
    -0.68
    POSITIVE LOGITS
     alot
    1.32
     thats
    1.31
     doesnt
    1.29
     ie
    1.23
     dont
    1.23
     haha
    1.22
     whats
    1.21
     lol
    1.19
     tho
    1.18
     didnt
    1.16
    Activations Density 0.970%

    No Known Activations