© 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. 4-RES-JB
    11. 2542
    Prev
    Next
    INDEX
    Explanations

    phrases containing the substring "ess"

    oai_token-act-pair · gpt-3.5-turbo

    words that denote a state of being or quality

    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
    ãĥ£
    -0.84
    oston
    -0.77
    osta
    -0.74
    vernment
    -0.72
    MSN
    -0.72
    undai
    -0.67
    ORN
    -0.66
    icultural
    -0.66
    hyde
    -0.66
    Äĩ
    -0.66
    POSITIVE LOGITS
    entials
    1.45
    entially
    1.30
    ential
    1.15
    enger
    1.15
    andro
    0.94
    ence
    0.92
    ages
    0.89
    ives
    0.89
    atisf
    0.88
    ÑĮ
    0.87
    Activations Density 0.018%

    No Known Activations