© 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. 8-RES-JB
    11. 14853
    Prev
    Next
    INDEX
    Explanations

    verbs related to movement or action away or towards something

    oai_token-act-pair · gpt-3.5-turbo

    variations of verbs that imply movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EntityItem
    -0.64
     pronounced
    -0.63
    rators
    -0.60
     corpus
    -0.59
    usable
    -0.57
    arov
    -0.57
    byn
    -0.55
    orate
    -0.55
    ervation
    -0.55
    YES
    -0.55
    POSITIVE LOGITS
     away
    1.09
     toward
    0.98
     hither
    0.96
     into
    0.96
     towards
    0.96
     downhill
    0.90
     onward
    0.89
     Away
    0.87
     onwards
    0.86
    away
    0.83
    Activations Density 0.142%

    No Known Activations