© 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. 4-RES-JB
    6. 424
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and problem-solving

    oai_token-act-pair · gpt-3.5-turbo

    discussions on strategies for handling challenges

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

    No Comments

    Negative Logits
    ortium
    -0.56
     Latest
    -0.52
     Nay
    -0.52
     Originally
    -0.51
     Shiite
    -0.50
     Nationwide
    -0.50
     reportedly
    -0.49
     Joint
    -0.49
    nsic
    -0.49
     Ronald
    -0.48
    POSITIVE LOGITS
     desired
    0.64
     predetermined
    0.62
    actual
    0.61
    )).
    0.60
     oneself
    0.59
     interact
    0.57
     behaviours
    0.56
     subconscious
    0.55
     skill
    0.54
     outweigh
    0.53
    Activations Density 2.632%

    No Known Activations