© 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. 11-RES-JB
    11. 4161
    Prev
    Next
    INDEX
    Explanations

    phrases related to verification or truth

    oai_token-act-pair · gpt-3.5-turbo

    terms related to verifiability and truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ered
    -0.73
    ERC
    -0.62
     courts
    -0.62
     Warriors
    -0.61
     listen
    -0.61
     hybrids
    -0.60
     listening
    -0.60
     SEM
    -0.59
     Werner
    -0.58
     Pearce
    -0.58
    POSITIVE LOGITS
    ifiable
    1.46
    itable
    1.44
    itably
    1.24
    bat
    1.21
    acity
    1.19
    gence
    1.08
    anda
    1.06
    million
    1.04
    ulent
    1.00
    ging
    1.00
    Activations Density 0.031%

    No Known Activations