© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 24165
    Prev
    Next
    INDEX
    Explanations

    specific terms related to various societal topics and concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific evidence and research

    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
    tnc
    -0.55
     fame
    -0.52
    ãģ¾
    -0.49
    âĵĺ
    -0.46
     hers
    -0.44
    idden
    -0.43
    burning
    -0.42
    pron
    -0.42
     eternity
    -0.42
     respectively
    -0.41
    POSITIVE LOGITS
     Pwr
    0.50
    nces
    0.49
     citiz
    0.49
    bender
    0.49
    terness
    0.47
    etheless
    0.46
     Webs
    0.44
    anyahu
    0.43
     glim
    0.42
     QUEST
    0.41
    Activations Density 4.966%

    No Known Activations