© 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. 7-RES-JB
    6. 1617
    Prev
    Next
    INDEX
    Explanations

    grammatical patterns and errors, especially related to punctuation and syntax

    oai_token-act-pair · gpt-3.5-turbo

    grammatical structures and errors in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awei
    -0.88
    jri
    -0.87
    scl
    -0.80
    Offline
    -0.79
    roxy
    -0.77
    CVE
    -0.76
     Skydragon
    -0.75
    Monitor
    -0.74
    IED
    -0.74
    ONSORED
    -0.73
    POSITIVE LOGITS
     phrases
    1.15
     syntax
    1.13
     spelling
    1.07
     grammar
    1.03
     formatting
    1.02
     phrase
    0.99
     text
    0.99
     delim
    0.96
     sentences
    0.96
     parsing
    0.96
    Activations Density 0.225%

    No Known Activations