© 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. 8-RES-JB
    6. 684
    Prev
    Next
    INDEX
    Explanations

    adjectives that emphasize a certain quality or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    modifiers that emphasize the intensity or significance of a situation

    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
    pei
    -0.65
    egu
    -0.64
    ools
    -0.62
    ĺħ
    -0.60
    folios
    -0.59
    ipedia
    -0.58
    vell
    -0.56
    acebook
    -0.56
    engine
    -0.55
    ©¶æ
    -0.55
    POSITIVE LOGITS
     than
    1.33
    than
    1.11
     Than
    0.93
    iating
    0.67
    enance
    0.65
    romeda
    0.64
    Ø©
    0.64
    amus
    0.63
     awaits
    0.62
     awaited
    0.61
    Activations Density 0.225%

    No Known Activations