© 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. 11546
    Prev
    Next
    INDEX
    Explanations

    phrases related to presenting information or findings, such as "present their findings" or "submit a report"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to presenting reports or findings

    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
    paces
    -0.75
    ucket
    -0.72
    enty
    -0.67
     befriend
    -0.67
    watching
    -0.66
    ometimes
    -0.63
    Timer
    -0.62
     Painter
    -0.62
    ionage
    -0.61
    chester
    -0.60
    POSITIVE LOGITS
     proposal
    1.39
     proposals
    1.37
     manuscript
    1.35
     results
    1.29
     findings
    1.27
     recommendations
    1.23
     conclusions
    1.19
     verdict
    1.17
     dossier
    1.13
     specifications
    1.12
    Activations Density 0.629%

    No Known Activations