© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5714
    Prev
    Next
    INDEX
    Explanations

    text that is closely related to other concepts or topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a strong connection or association between concepts

    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
    inous
    -0.76
     abundantly
    -0.72
    acity
    -0.71
    ICAN
    -0.68
     Bucket
    -0.67
    xit
    -0.67
    acious
    -0.66
    amaz
    -0.66
    RAW
    -0.65
    eva
    -0.64
    POSITIVE LOGITS
     resemble
    1.02
     resembles
    1.00
     aligned
    0.96
     monitored
    0.96
     guarded
    0.95
     resembled
    0.95
     scrutin
    0.93
     spaced
    0.92
     resembling
    0.91
     watched
    0.90
    Activations Density 0.044%

    No Known Activations