© 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. 9-RES-JB
    11. 9901
    Prev
    Next
    INDEX
    Explanations

    the word "essence" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to essentiality or core qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MSN
    -0.75
    ãĥ£
    -0.74
    vernment
    -0.73
     vitro
    -0.69
    webkit
    -0.63
    bing
    -0.61
    =-=-=-=-
    -0.61
    ASED
    -0.61
    Äĩ
    -0.60
    tsy
    -0.60
    POSITIVE LOGITS
    entials
    1.44
    entially
    1.39
    enger
    1.22
    andro
    1.18
    ential
    1.10
    omething
    1.09
    ources
    1.01
    ence
    0.97
    ively
    0.96
    ages
    0.95
    Activations Density 0.047%

    No Known Activations