© 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. 22620
    Prev
    Next
    INDEX
    Explanations

    lists of items related to a specific topic or category

    oai_token-act-pair · gpt-3.5-turbo

    references to lists or collections of items

    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
    pees
    -0.72
    haul
    -0.70
    awk
    -0.70
    bah
    -0.68
    pter
    -0.68
    olding
    -0.67
    enser
    -0.67
    cffffcc
    -0.66
    construct
    -0.66
    raid
    -0.65
    POSITIVE LOGITS
     listed
    0.87
     eligible
    0.85
     nearest
    0.84
    eries
    0.83
     vying
    0.82
    hips
    0.81
     currently
    0.81
     grouped
    0.80
     whose
    0.77
     categorized
    0.76
    Activations Density 0.386%

    No Known Activations