© 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. 8937
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and financial matters

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or financial implications and assessments

    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
    â̦)
    -0.73
    iaries
    -0.66
    !)
    -0.64
     *)
    -0.62
    ...)
    -0.62
    )"
    -0.58
    )|
    -0.58
    ?)
    -0.58
     Dise
    -0.57
    ffen
    -0.54
    POSITIVE LOGITS
    etheless
    1.01
     nonetheless
    0.67
    åĮ
    0.61
    èĢ
    0.60
     nevertheless
    0.59
    NetMessage
    0.58
    addon
    0.56
    å®
    0.56
     respectively
    0.54
     comparatively
    0.54
    Activations Density 2.813%

    No Known Activations