© 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. 17838
    Prev
    Next
    INDEX
    Explanations

    mentions of incompleteness or imperfection in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to data quality issues or deficiency

    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
    Reviewer
    -0.75
    issue
    -0.70
    urai
    -0.69
    lua
    -0.69
    Issue
    -0.68
    ocard
    -0.68
    urg
    -0.68
    DH
    -0.67
    ħĭ
    -0.67
    uddin
    -0.66
    POSITIVE LOGITS
     incomplete
    1.01
    uously
    0.87
    ly
    0.81
    uous
    0.79
     adolesc
    0.76
     imperfect
    0.72
    kered
    0.70
    nesses
    0.69
    oing
    0.68
     unfinished
    0.67
    Activations Density 0.013%

    No Known Activations