© 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. 17194
    Prev
    Next
    INDEX
    Explanations

    attributes or characteristics of physical objects

    oai_token-act-pair · gpt-3.5-turbo

    descriptive elements related to physical appearances or conditions

    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
    =-=-=-=-=-=-=-=-
    -0.80
    ILLE
    -0.76
     duties
    -0.73
     privileges
    -0.72
    reon
    -0.71
     schedules
    -0.69
     logistics
    -0.69
     classics
    -0.68
    OUP
    -0.67
     manuals
    -0.65
    POSITIVE LOGITS
     protr
    1.09
     resembling
    0.95
     shimmer
    0.92
     streaks
    0.91
     forming
    0.91
     formed
    0.90
     swirl
    0.89
     flakes
    0.89
    burst
    0.89
     swirling
    0.88
    Activations Density 0.251%

    No Known Activations