© 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. 20397
    Prev
    Next
    INDEX
    Explanations

    phrases related to concerns, issues, or disruptions

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments or issues related to safety and disruptions

    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
    liam
    -0.71
    eele
    -0.66
    ortment
    -0.63
    igham
    -0.60
    fw
    -0.59
    acha
    -0.58
    itled
    -0.57
    ku
    -0.57
    tsky
    -0.56
    ethyl
    -0.56
    POSITIVE LOGITS
     whatsoever
    1.72
     nor
    1.57
     anymore
    1.46
    nor
    1.01
     anything
    1.00
     slightest
    0.98
     anybody
    0.95
     either
    0.95
     anywhere
    0.93
     except
    0.87
    Activations Density 0.264%

    No Known Activations