© 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. 5041
    Prev
    Next
    INDEX
    Explanations

    phrases indicating speculation or deduction

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the structure "must have" to indicate assumptions or conclusions about past actions

    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
     Mold
    -0.68
    ashi
    -0.65
    cular
    -0.64
    opian
    -0.64
    pell
    -0.63
    ackle
    -0.63
    oneliness
    -0.62
    traditional
    -0.60
    paper
    -0.60
    pend
    -0.58
    POSITIVE LOGITS
    ï¸
    0.64
    isan
    0.60
    cia
    0.59
     AG
    0.59
    asta
    0.57
    ECA
    0.56
    ns
    0.54
    Acknowled
    0.54
    tek
    0.54
     Sens
    0.54
    Activations Density 0.078%

    No Known Activations