© 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. 12135
    Prev
    Next
    INDEX
    Explanations

    links or calls to action in text

    oai_token-act-pair · gpt-3.5-turbo

    call-to-action phrases related to subscriptions and policies

    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
    lished
    -0.72
    aughs
    -0.65
    ictionary
    -0.56
    coins
    -0.55
     synopsis
    -0.55
     Somers
    -0.55
    ================================================================
    -0.54
     Dictionary
    -0.54
    zhen
    -0.53
    whe
    -0.52
    POSITIVE LOGITS
    asin
    0.64
     DEFENSE
    0.59
     >>>
    0.57
    >>>
    0.53
    Write
    0.52
     reinforcement
    0.52
     bond
    0.51
    ><
    0.49
    Enable
    0.49
    ptive
    0.48
    Activations Density 0.061%

    No Known Activations