© 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. 2-RES-JB
    11. 4411
    Prev
    Next
    INDEX
    Explanations

    adjectives related to feeling exhausted or fatigued

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'tired'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    authorized
    -0.79
    byter
    -0.77
    iola
    -0.69
    izations
    -0.68
    vernment
    -0.66
    tein
    -0.66
    redit
    -0.64
    basketball
    -0.64
     charism
    -0.64
     magnitude
    -0.63
    POSITIVE LOGITS
     tired
    1.03
    igue
    1.03
    rums
    0.80
     old
    0.78
    åĭ
    0.74
    ness
    0.74
     clich
    0.72
     stale
    0.71
    bones
    0.69
    nesses
    0.69
    Activations Density 0.007%

    No Known Activations