© 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. 2655
    Prev
    Next
    INDEX
    Explanations

    actions or processes that involve changing the physical state or condition of something

    oai_token-act-pair · gpt-3.5-turbo

    gerunds that denote actions or processes related to various activities and tasks

    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
    eria
    -0.84
    iland
    -0.74
    si
    -0.72
     proceeding
    -0.69
    emale
    -0.69
    raltar
    -0.69
    nings
    -0.67
    elo
    -0.67
    termination
    -0.67
    sis
    -0.66
    POSITIVE LOGITS
     oneself
    1.06
     them
    0.95
     chunks
    0.77
     yourself
    0.73
     fewer
    0.71
     individuals
    0.71
     certain
    0.70
     outdated
    0.68
     passages
    0.68
     ourselves
    0.67
    Activations Density 0.249%

    No Known Activations