© 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. 17313
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal reflections and experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal emotional experiences and reflections

    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
    £ı
    -0.69
    ardless
    -0.67
     overseen
    -0.66
    æ©Ł
    -0.66
    arez
    -0.63
     duly
    -0.63
     championed
    -0.62
    ivably
    -0.61
    vernment
    -0.60
     stewards
    -0.60
    POSITIVE LOGITS
     me
    1.63
     my
    1.16
     him
    1.03
    him
    0.92
     us
    0.89
     mine
    0.83
    My
    0.81
     waking
    0.80
    me
    0.80
     nerve
    0.77
    Activations Density 0.333%

    No Known Activations