© 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. 8-RES-JB
    11. 24032
    Prev
    Next
    INDEX
    Explanations

    mentions of common prefixes/suffixes such as 'cor', 'on', and 'ation'

    oai_token-act-pair · gpt-3.5-turbo

    the word "on" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.75
    Berry
    -0.69
    Redd
    -0.69
    Known
    -0.63
    XL
    -0.58
    unknown
    -0.58
    gerald
    -0.57
    razil
    -0.56
     statically
    -0.56
     Pigs
    -0.56
    POSITIVE LOGITS
    etheless
    0.92
    autical
    0.80
    ique
    0.78
    imity
    0.78
    ucle
    0.76
    iability
    0.76
    uclear
    0.75
    ation
    0.74
    otation
    0.74
    acci
    0.73
    Activations Density 0.074%

    No Known Activations