© 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. 11310
    Prev
    Next
    INDEX
    Explanations

    phrases indicating different levels or stages of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating thresholds or levels of measurement

    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
     indications
    -0.69
    packages
    -0.66
    evidence
    -0.63
    enegger
    -0.61
     Orders
    -0.60
     invitations
    -0.59
     instructions
    -0.59
     constructs
    -0.59
     examples
    -0.58
    NP
    -0.57
    POSITIVE LOGITS
    venge
    1.51
    rouse
    1.16
     halt
    0.96
     predetermined
    0.96
     manageable
    0.86
     point
    0.82
     coma
    0.79
     lesser
    0.79
     certain
    0.78
     whopping
    0.77
    Activations Density 0.122%

    No Known Activations