© 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. 2-RES-JB
    11. 1572
    Prev
    Next
    INDEX
    Explanations

    sentences referring to legal sentences and proceedings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Sent" in various contexts, likely related to sentencing or legal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARDS
    -0.79
    orsi
    -0.77
    ãģį
    -0.67
     Ludwig
    -0.66
    OSS
    -0.65
    PHOTOS
    -0.63
    姫
    -0.62
    ARD
    -0.62
    OO
    -0.61
    ILD
    -0.60
    POSITIVE LOGITS
    inel
    1.39
     Sent
    1.15
    Sent
    1.10
    sent
    1.06
    iments
    0.99
    encing
    0.97
    imental
    0.89
    iment
    0.88
    enced
    0.86
    entious
    0.86
    Activations Density 0.010%

    No Known Activations