© 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. 6809
    Prev
    Next
    INDEX
    Explanations

    mentions of ongoing or continued actions or events with a focus on development or progression

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of continuation or maintaining an ongoing process

    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
    azines
    -0.75
    iencies
    -0.71
    rien
    -0.67
    acus
    -0.67
    vil
    -0.65
    encers
    -0.62
    ustomed
    -0.61
    ye
    -0.61
    hest
    -0.61
    bi
    -0.61
    POSITIVE LOGITS
     thereof
    0.95
     continuation
    0.87
    uality
    0.87
    xual
    0.85
    SHIP
    0.84
    akeru
    0.79
    noon
    0.78
    theless
    0.78
     ende
    0.78
    alist
    0.77
    Activations Density 0.014%

    No Known Activations