© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 3667
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to clarity or lack of clarity in a context

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to clarity and understanding

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

    No Comments

    Negative Logits
     Bellev
    -0.73
    ammad
    -0.71
    don
    -0.69
    anova
    -0.66
    Lie
    -0.65
    unte
    -0.65
    cele
    -0.65
    arte
    -0.62
    Particip
    -0.61
     gangs
    -0.61
    POSITIVE LOGITS
    20439
    1.12
     clarity
    1.06
    mares
    0.86
    ible
    0.84
     MX
    0.74
    istically
    0.72
    ively
    0.72
     assurance
    0.72
    \\\\\\\\
    0.71
    \\\\\\\\\\\\\\\\
    0.71
    Activations Density 0.022%

    No Known Activations