© 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. 2753
    Prev
    Next
    INDEX
    Explanations

    phrases related to authorship or attribution in documents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "for" in various contexts

    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
    soever
    -0.75
     [+
    -0.67
     quo
    -0.65
     alive
    -0.64
    hazard
    -0.64
    ynski
    -0.63
     nevertheless
    -0.63
    ÃŁ
    -0.62
    egu
    -0.61
    ptions
    -0.61
    POSITIVE LOGITS
    geries
    1.23
    bidden
    0.91
    gery
    0.87
     inclusion
    0.85
    imeo
    0.81
     Collider
    0.73
     listeners
    0.73
     sale
    0.70
     viewers
    0.69
    ummies
    0.69
    Activations Density 0.208%

    No Known Activations