© 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. 20301
    Prev
    Next
    INDEX
    Explanations

    numerical lists with varying emphasis points

    oai_token-act-pair · gpt-3.5-turbo

    instances of numbered lists or itemized points

    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
    arial
    -0.75
    izations
    -0.70
    scenes
    -0.65
    erity
    -0.61
    akings
    -0.60
    ties
    -0.59
    cellaneous
    -0.59
    awaru
    -0.58
    gone
    -0.58
     fences
    -0.57
    POSITIVE LOGITS
    st
    1.23
    Password
    1.13
     Corinthians
    1.12
    120
    0.88
    125
    0.88
     Introduction
    0.84
    ST
    0.83
     Timothy
    0.81
    123
    0.80
    128
    0.78
    Activations Density 0.043%

    No Known Activations