© 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. 0-RES-JB
    11. 8395
    Prev
    Next
    INDEX
    Explanations

    phrases associated with critiques or criticisms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of critics and their evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alert
    -0.69
    rex
    -0.68
     âĸĪ
    -0.65
    full
    -0.63
    shi
    -0.61
    nm
    -0.61
     Kis
    -0.59
    cycle
    -0.59
     Volunte
    -0.59
    rax
    -0.58
    POSITIVE LOGITS
     critics
    3.79
     detractors
    2.96
     Critics
    2.58
    Critics
    2.42
     skeptics
    2.13
     critic
    2.12
     opponents
    2.03
     reviewers
    1.97
     criticisms
    1.89
     proponents
    1.87
    Activations Density 0.013%

    No Known Activations