© 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. 2433
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant or impactful moments

    oai_token-act-pair · gpt-3.5-turbo

    references to significant or pivotal moments in various contexts

    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
    yu
    -0.78
    raid
    -0.75
    ply
    -0.75
    abet
    -0.72
    uct
    -0.70
    achev
    -0.70
    yss
    -0.70
    GE
    -0.70
    emale
    -0.70
    uv
    -0.69
    POSITIVE LOGITS
     moments
    1.28
     Moments
    1.19
     moment
    0.94
     glimps
    0.93
    hift
    0.92
    aneously
    0.90
     reminders
    0.87
     Minutes
    0.87
     Moment
    0.84
     milestones
    0.84
    Activations Density 0.013%

    No Known Activations