© 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. 0-RES-JB
    6. 22718
    Prev
    Next
    INDEX
    Explanations

    mentions of the NBC network

    oai_token-act-pair · gpt-3.5-turbo

    references to NBC or its related programming and personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iang
    -0.87
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.76
    xus
    -0.74
    Sword
    -0.70
     Carbuncle
    -0.69
    gger
    -0.68
    minist
    -0.68
    Tang
    -0.67
     sword
    -0.67
    avers
    -0.67
    POSITIVE LOGITS
     NBC
    3.60
    NBC
    2.71
     CBS
    2.17
     ABC
    2.01
     MSNBC
    1.94
     CNBC
    1.88
     ITV
    1.83
     FOX
    1.76
    CBS
    1.70
    ABC
    1.63
    Activations Density 0.020%

    No Known Activations