© 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. 4-RES-JB
    11. 14844
    Prev
    Next
    INDEX
    Explanations

    questions directed at oneself or others

    oai_token-act-pair · gpt-3.5-turbo

    questions directed at oneself or others

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

    No Comments

    Negative Logits
    requires
    -0.70
     Till
    -0.65
    inction
    -0.63
    ushima
    -0.60
    BuyableInstoreAndOnline
    -0.59
     hepat
    -0.59
     Dock
    -0.59
    Sax
    -0.58
     NETWORK
    -0.58
     Thumbnails
    -0.57
    POSITIVE LOGITS
     forgiveness
    0.74
     probing
    0.74
     questions
    0.73
    Origin
    0.72
    DERR
    0.71
    asking
    0.71
    autions
    0.70
     politely
    0.70
    uru
    0.69
    xus
    0.69
    Activations Density 0.228%

    No Known Activations