© 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. 18555
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a division or categorization of items into two distinct groups

    oai_token-act-pair · gpt-3.5-turbo

    classifications or categories and how they can be divided

    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
     wonders
    -0.70
     pores
    -0.70
    daq
    -0.65
    boards
    -0.65
     certs
    -0.61
    board
    -0.59
     understatement
    -0.59
    lves
    -0.58
     rattled
    -0.58
     everywhere
    -0.58
    POSITIVE LOGITS
     Firstly
    1.28
    Firstly
    0.98
     namely
    0.89
     First
    0.85
     Either
    0.84
     Ones
    0.77
    hemat
    0.72
    first
    0.70
    First
    0.69
    thodox
    0.66
    Activations Density 0.158%

    No Known Activations