© 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. 10-RES-JB
    6. 18536
    Prev
    Next
    INDEX
    Explanations

    details about academic achievements and qualifications

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the article "a" used 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
    terday
    -0.80
    agents
    -0.74
     idiots
    -0.68
    enemy
    -0.67
    cause
    -0.67
     Izan
    -0.67
    Americans
    -0.66
    evidence
    -0.66
    votes
    -0.64
    inventoryQuantity
    -0.64
    POSITIVE LOGITS
     penchant
    1.14
     knack
    1.11
     reputation
    1.06
     stint
    1.02
     plethora
    1.01
     slew
    0.98
     thriving
    0.98
     lifelong
    0.98
     fascination
    0.95
     whopping
    0.95
    Activations Density 0.260%

    No Known Activations