© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5993
    Prev
    Next
    INDEX
    Explanations

    names and locations related to various individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of artists and specific artistic styles or mediums

    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
     corrid
    -0.79
     skelet
    -0.70
     referen
    -0.68
     challeng
    -0.67
     millenn
    -0.63
    staking
    -0.61
     conclud
    -0.61
     suspic
    -0.59
     helicop
    -0.58
    PDATE
    -0.57
    POSITIVE LOGITS
    insk
    0.64
    ®
    0.64
    oglu
    0.63
    aya
    0.62
    ai
    0.61
    aten
    0.60
    ui
    0.58
    aii
    0.58
     County
    0.57
    ayan
    0.57
    Activations Density 0.490%

    No Known Activations