© 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. 10-RES-JB
    11. 11052
    Prev
    Next
    INDEX
    Explanations

    sequences with specific numerical patterns

    oai_token-act-pair · gpt-3.5-turbo

    formatted data or lists involving brackets and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blot
    -0.75
     Hulk
    -0.73
    baum
    -0.71
     nu
    -0.66
    otine
    -0.65
     Viet
    -0.65
    hower
    -0.64
     bell
    -0.63
     breathing
    -0.62
    heit
    -0.62
    POSITIVE LOGITS
    14
    1.45
    13
    1.41
     14
    1.27
     13
    1.21
    139
    1.07
    15
    1.07
    130
    1.05
    138
    1.01
    134
    1.00
    140
    0.97
    Activations Density 0.096%

    No Known Activations