© 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. 19042
    Prev
    Next
    INDEX
    Explanations

    phrases related to cause and effect or methods to achieve outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a process or action conducted by means of something

    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
    ilight
    -0.77
    estamp
    -0.68
    swers
    -0.68
    ILLE
    -0.67
    hound
    -0.66
    ERROR
    -0.66
    hunt
    -0.65
    atron
    -0.65
    iffe
    -0.65
    oom
    -0.64
    POSITIVE LOGITS
     intermedi
    0.86
     sheer
    0.85
     attrition
    0.78
     inaction
    0.76
     taxation
    0.73
     various
    0.73
     negotiation
    0.73
     acquisitions
    0.72
    gone
    0.72
     repetition
    0.71
    Activations Density 0.074%

    No Known Activations