© 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. 9-RES-JB
    11. 8623
    Prev
    Next
    INDEX
    Explanations

    numerical information related to rankings, distances, time, or progress

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to scores and game metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acus
    -0.70
    ghazi
    -0.66
    aca
    -0.64
    ãĤ´ãĥ³
    -0.62
    1920
    -0.61
     BaseType
    -0.60
     Binding
    -0.59
    alam
    -0.59
    unci
    -0.59
    orescence
    -0.58
    POSITIVE LOGITS
     away
    1.24
     ahead
    1.16
     shy
    1.12
     ago
    1.10
     Away
    1.08
     apart
    0.99
     removed
    0.98
     overdue
    0.94
     wiser
    0.93
     slower
    0.91
    Activations Density 0.183%

    No Known Activations