© 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. 10-RES-JB
    11. 3178
    Prev
    Next
    INDEX
    Explanations

    words related to benefits or advantages

    oai_token-act-pair · gpt-3.5-turbo

    terms related to advantages and benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lio
    -0.80
    inarily
    -0.67
    Untitled
    -0.66
    oths
    -0.60
    prep
    -0.59
     slightest
    -0.59
     delinquent
    -0.59
     Frie
    -0.59
    lem
    -0.58
    INE
    -0.58
    POSITIVE LOGITS
     outweigh
    1.34
     outwe
    1.26
     Flavoring
    0.84
     thereof
    0.82
     inherent
    0.80
     conferred
    0.80
     abound
    0.77
    onential
    0.75
    fulness
    0.72
     of
    0.69
    Activations Density 0.114%

    No Known Activations