© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 3572
    Prev
    Next
    INDEX
    Explanations

    phrases related to the overall evaluation or assessment of various entities

    oai_token-act-pair · gpt-3.5-turbo

    references to "overall" assessments across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Caf
    -0.83
     Debor
    -0.76
     Bry
    -0.71
     Frie
    -0.69
    rette
    -0.67
    isters
    -0.66
     Yel
    -0.64
     Speedway
    -0.63
    aunts
    -0.63
     Mub
    -0.63
    POSITIVE LOGITS
     stability
    0.82
     attractiveness
    0.81
     satisfaction
    0.80
     impression
    0.79
     improvement
    0.78
     momentum
    0.78
     usefulness
    0.78
     consensus
    0.78
     imbalance
    0.78
     equilibrium
    0.78
    Activations Density 0.022%

    No Known Activations