© 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. 7-RES-JB
    6. 183
    Prev
    Next
    INDEX
    Explanations

    phrases related to the creation or establishment of something for a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    references to rules, regulations, or laws that address specific behaviors or practices

    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
    etheless
    -0.69
    Scroll
    -0.68
    Available
    -0.62
    patch
    -0.61
     Usage
    -0.60
     knots
    -0.60
    lag
    -0.59
     wrinkles
    -0.59
     Earthqu
    -0.58
     Coverage
    -0.58
    POSITIVE LOGITS
     intentionally
    0.83
     purpose
    0.80
     expressly
    0.78
     acquaint
    0.77
     revenge
    0.76
     purposely
    0.76
     purely
    0.74
     intending
    0.74
     purposefully
    0.73
     circumvent
    0.73
    Activations Density 0.899%

    No Known Activations