© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22978
    Prev
    Next
    INDEX
    Explanations

    words related to progress, advancement, or growth

    oai_token-act-pair · gpt-3.5-turbo

    terms related to growth and presence in various contexts

    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
     deliberate
    -0.61
    imar
    -0.58
    ©¶æ
    -0.58
    inflamm
    -0.57
     severe
    -0.57
    cise
    -0.56
     Grain
    -0.55
     plague
    -0.55
     wipes
    -0.54
    tein
    -0.54
    POSITIVE LOGITS
     overseas
    0.98
     internationally
    0.90
    hare
    0.87
     abroad
    0.86
     globally
    0.77
     domestically
    0.76
     elsewhere
    0.75
     amidst
    0.73
     worldwide
    0.72
     Emerging
    0.71
    Activations Density 0.395%

    No Known Activations