© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1772
    Prev
    Next
    INDEX
    Explanations

    names of people or entities ending with 'arenko'

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srfAttach
    -0.72
     Accuracy
    -0.70
     extent
    -0.61
     Mankind
    -0.60
    UGE
    -0.60
     Kinnikuman
    -0.59
     degree
    -0.58
     magnitude
    -0.58
     coord
    -0.56
     catch
    -0.55
    POSITIVE LOGITS
    thal
    0.87
    wana
    0.85
    stant
    0.84
    bent
    0.83
    ski
    0.82
    rien
    0.81
    ko
    0.81
    thro
    0.79
    ites
    0.79
    swer
    0.79
    Activations Density 0.006%

    No Known Activations