© 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. 7-RES-JB
    11. 2642
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal notices or claims

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Allegations."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wilde
    -0.65
    ulates
    -0.61
    ISM
    -0.60
    nown
    -0.60
    ulate
    -0.58
     deft
    -0.58
    culosis
    -0.57
     snug
    -0.57
     dism
    -0.56
     Strait
    -0.56
    POSITIVE LOGITS
    edly
    1.07
    heny
    0.91
    ations
    0.87
    iance
    0.86
    iant
    0.82
    algia
    0.81
    uve
    0.77
    ationally
    0.76
    yet
    0.76
    alg
    0.74
    Activations Density 0.055%

    No Known Activations