© 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. 8-RES-JB
    11. 6364
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of liberation or liberty

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Liber" and its variations, indicating a focus on themes related to liberty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.86
    enegger
    -0.77
    older
    -0.76
    è¦ļéĨĴ
    -0.72
    EED
    -0.67
    REE
    -0.65
    NetMessage
    -0.64
    wow
    -0.63
    orney
    -0.63
     à¨
    -0.62
    POSITIVE LOGITS
    tarians
    1.30
    tarian
    1.11
    gence
    1.07
    ator
    0.95
    ty
    0.94
    itas
    0.93
    ations
    0.91
    eer
    0.90
    mented
    0.87
    ated
    0.85
    Activations Density 0.038%

    No Known Activations