© 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. 4-RES-JB
    11. 7286
    Prev
    Next
    INDEX
    Explanations

    verbs related to ongoing actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles relating to actions and involvement

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

    No Comments

    Negative Logits
    ifi
    -0.90
    iosis
    -0.86
    asus
    -0.86
    ulic
    -0.86
    elo
    -0.85
    inctions
    -0.82
    haps
    -0.79
    ruary
    -0.79
    osate
    -0.79
    mington
    -0.79
    POSITIVE LOGITS
     ability
    0.90
     tendency
    0.88
     realization
    0.84
     element
    0.84
     aspect
    0.84
     sphere
    0.83
     circle
    0.83
     assumption
    0.83
     mechanism
    0.82
     agent
    0.80
    Activations Density 0.256%

    No Known Activations