© 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. 23717
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases indicating a physical or emotional impact

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods, indicating sentence endings

    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
    ĸļ
    -0.75
    ãĤ«
    -0.65
     allowance
    -0.65
    å§
    -0.64
    ³
    -0.62
    encia
    -0.61
     exting
    -0.61
    Ĺ
    -0.60
    å¿
    -0.60
    UFF
    -0.60
    POSITIVE LOGITS
     Maybe
    1.10
     Either
    1.08
     Alternatively
    1.02
     Perhaps
    1.00
    perhaps
    1.00
     Regardless
    0.99
     Possibly
    0.99
    maybe
    0.97
     depending
    0.95
     Or
    0.93
    Activations Density 0.788%

    No Known Activations