© 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. 8-RES-JB
    11. 6084
    Prev
    Next
    INDEX
    Explanations

    references to financial or business-related terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    events related to significant moments or circumstances

    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
    taboola
    -0.80
    lihood
    -0.80
    catentry
    -0.76
    20439
    -0.74
    ĸ
    -0.65
    ĪĴ
    -0.65
    actionDate
    -0.65
     [|
    -0.63
     externalToEVAOnly
    -0.61
     thereto
    -0.60
    POSITIVE LOGITS
    !
    1.02
    !!!
    1.02
    !!!!
    0.98
    !!!!!
    0.93
    !'
    0.92
    !:
    0.91
    ?!
    0.91
    !!!!!!!!
    0.89
    !!
    0.87
    !?
    0.86
    Activations Density 0.748%

    No Known Activations