© 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. 16734
    Prev
    Next
    INDEX
    Explanations

    phrases related to the persistence or prevalence of certain phenomena over time

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to the persistence of issues and changes over time

    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
    itialized
    -0.73
     eventual
    -0.69
     finished
    -0.64
    HAHAHAHA
    -0.64
     Genie
    -0.60
     FINAL
    -0.60
     previous
    -0.59
     subsequ
    -0.59
     goodness
    -0.58
     FIRST
    -0.58
    POSITIVE LOGITS
     unab
    0.83
    despite
    0.83
     nowadays
    0.82
     despite
    0.80
     unchecked
    0.79
     abroad
    0.76
     amid
    0.76
     owing
    0.75
     geographically
    0.75
     anymore
    0.74
    Activations Density 0.510%

    No Known Activations