© 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. 11269
    Prev
    Next
    INDEX
    Explanations

    verbs ending in 'ing' related to physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles in various contexts

    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
    ¿½
    -0.84
    ãĥķãĤ©
    -0.82
    avier
    -0.79
    peria
    -0.77
    éĸ
    -0.77
    shown
    -0.76
    redo
    -0.75
    igmatic
    -0.75
    saf
    -0.75
    elin
    -0.74
    POSITIVE LOGITS
     furiously
    1.08
     around
    1.06
     frantically
    1.01
     hay
    0.92
     ducks
    0.91
     hither
    0.88
     maniac
    0.88
     idiots
    0.85
     away
    0.85
     gib
    0.85
    Activations Density 0.319%

    No Known Activations