© 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. 8-RES-JB
    11. 6097
    Prev
    Next
    INDEX
    Explanations

    phrases related to the usage or application of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "using"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    si
    -0.74
    merce
    -0.70
    hood
    -0.70
    alty
    -0.70
     greets
    -0.69
    wat
    -0.69
    hound
    -0.68
    naire
    -0.68
     accompanies
    -0.67
    itialized
    -0.65
    POSITIVE LOGITS
     methods
    0.80
     techniques
    0.77
     pipes
    0.74
     combinations
    0.74
    fully
    0.71
     technologies
    0.71
     PowerShell
    0.69
     coupons
    0.69
     aliases
    0.68
    FUL
    0.68
    Activations Density 0.067%

    No Known Activations