© 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. 10915
    Prev
    Next
    INDEX
    Explanations

    information about specific locations and people, such as press releases and personal details

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or formatting anomaly in the text

    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
     mathemat
    -0.84
     disadvant
    -0.76
     carbohyd
    -0.75
     accomp
    -0.70
    angan
    -0.68
    chwitz
    -0.63
    oken
    -0.63
     incent
    -0.63
    akening
    -0.60
    inav
    -0.59
    POSITIVE LOGITS
    ï¸ı
    0.98
    fter
    0.81
    ese
    0.73
    ï¸
    0.70
    rous
    0.69
    ence
    0.68
    ð
    0.66
     denotes
    0.66
     Torrent
    0.65
    shire
    0.64
    Activations Density 0.104%

    No Known Activations