© 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. 6-RES-JB
    6. 20333
    Prev
    Next
    INDEX
    Explanations

    phrases related to specialized task forces or committees

    oai_token-act-pair · gpt-3.5-turbo

    references to task forces and their activities

    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
    é¾įå
    -0.74
    ulia
    -0.73
    duc
    -0.72
    brew
    -0.69
    anes
    -0.66
    ãĤ¨ãĥ«
    -0.65
    esse
    -0.65
    pron
    -0.65
    æµ
    -0.64
    jar
    -0.64
    POSITIVE LOGITS
     convened
    1.08
     chaired
    1.03
     disbanded
    0.92
    naire
    0.91
    chairs
    0.88
     comprised
    0.88
     Chairman
    0.86
     Cosponsors
    0.85
     tasked
    0.84
     members
    0.84
    Activations Density 0.062%

    No Known Activations