© 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. 9-RES-JB
    11. 16168
    Prev
    Next
    INDEX
    Explanations

    technical and numerical information related to various topics, such as costs, measurements, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to consumption or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.75
     scapego
    -0.68
     blame
    -0.67
     reneg
    -0.66
    ZE
    -0.63
     acknowled
    -0.62
    particularly
    -0.61
     awaited
    -0.61
     announcements
    -0.60
     alliances
    -0.60
    POSITIVE LOGITS
     equivalent
    1.04
    average
    1.03
     average
    1.02
     multiplied
    0.97
    assuming
    0.93
     avg
    0.89
     equals
    0.88
     Average
    0.86
     Assuming
    0.86
    Average
    0.86
    Activations Density 0.867%

    No Known Activations