© 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. 10-RES-JB
    11. 8052
    Prev
    Next
    INDEX
    Explanations

    verbs related to action or progress

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases related to actions and events occurring or being reported

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aint
    -0.69
     qualifies
    -0.66
     theorem
    -0.61
    aintain
    -0.61
     violates
    -0.61
     qualify
    -0.58
     Achieve
    -0.58
     successor
    -0.57
     compare
    -0.57
    igrate
    -0.57
    POSITIVE LOGITS
     scarce
    1.30
     plentiful
    1.27
     abound
    1.12
     sparse
    1.10
     flowing
    1.04
     scant
    1.01
     sporadic
    0.97
     pouring
    0.92
     abundant
    0.91
     rife
    0.89
    Activations Density 0.227%

    No Known Activations