© 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. 6-RES-JB
    11. 19652
    Prev
    Next
    INDEX
    Explanations

    phrases related to using technology or tools

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the action of utilizing a specific tool or method

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uberty
    -0.76
    hound
    -0.75
    nesty
    -0.72
    cffffcc
    -0.72
    owship
    -0.70
    si
    -0.69
    merce
    -0.68
    hood
    -0.68
    naire
    -0.68
    mobi
    -0.67
    POSITIVE LOGITS
    FUL
    0.74
     sparing
    0.74
     borrowed
    0.71
     scissors
    0.69
     shortcuts
    0.68
     techniques
    0.67
     contacts
    0.67
     coupons
    0.67
    fully
    0.66
     condoms
    0.66
    Activations Density 0.055%

    No Known Activations