© 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. 8105
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing a specific point or cause

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "that"

    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
    apolis
    -0.74
    tones
    -0.74
    eteenth
    -0.73
    istor
    -0.72
    estern
    -0.71
    ourn
    -0.71
    byss
    -0.70
    ackets
    -0.69
    asures
    -0.68
    abee
    -0.68
    POSITIVE LOGITS
     includes
    1.40
     translates
    1.36
     means
    1.20
     entails
    1.18
     extends
    1.16
     constitutes
    1.16
     happens
    1.15
     brings
    1.14
     involves
    1.13
     applies
    1.13
    Activations Density 0.107%

    No Known Activations