© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 1438
    Prev
    Next
    INDEX
    Explanations

    words related to physical or abstract concepts or ideologies ending in 'ical'

    oai_token-act-pair · gpt-3.5-turbo

    words that are related to concepts in analysis and categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.88
    VPN
    -0.73
    ËĪ
    -0.72
    UTF
    -0.72
    GV
    -0.71
    IRD
    -0.70
    ·
    -0.68
    KEN
    -0.67
    VK
    -0.67
    legram
    -0.66
    POSITIVE LOGITS
    ical
    0.95
    ity
    0.95
    ities
    0.84
     Pwr
    0.83
    abama
    0.82
    ité
    0.82
    otine
    0.79
    ism
    0.76
    iliated
    0.76
    upe
    0.75
    Activations Density 0.016%

    No Known Activations