© 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. 11-RES-JB
    11. 22586
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or events happening to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words related to experiences of suffering and overcoming adversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    direction
    -0.79
    cation
    -0.78
    heit
    -0.77
    Interstitial
    -0.74
    bsp
    -0.74
    pmwiki
    -0.73
    aan
    -0.71
    ãĥ¯ãĥ³
    -0.71
    £ı
    -0.69
    imity
    -0.68
    POSITIVE LOGITS
     him
    1.22
     millions
    1.08
     countless
    1.05
     many
    1.03
     thousands
    0.98
     generations
    0.96
     me
    0.94
     tens
    0.89
     hundreds
    0.89
    him
    0.87
    Activations Density 0.416%

    No Known Activations