© 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. 6-RES-JB
    11. 23777
    Prev
    Next
    INDEX
    Explanations

    references to technology tools and software, particularly related to social media and file sharing

    oai_token-act-pair · gpt-3.5-turbo

    the presence of an end-of-text marker or signal indicating the conclusion of a text segment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outhern
    -0.76
     unborn
    -0.75
    oe
    -0.69
    selage
    -0.69
    ederal
    -0.68
    ãĥ¼
    -0.67
     disembark
    -0.65
    iscal
    -0.65
    itate
    -0.64
     wives
    -0.64
    POSITIVE LOGITS
     Browser
    0.96
    Platform
    0.88
     Server
    0.85
     Lite
    0.85
     Firefox
    0.84
     Streaming
    0.84
     CMS
    0.82
     Startup
    0.82
     Basics
    0.81
     Chrome
    0.81
    Activations Density 0.468%

    No Known Activations