Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13025
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing, editing, and producing content

    oai_token-act-pair · gpt-3.5-turbo

    activities or roles related to creative professions and production

    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
    ONSORED
    -1.04
    ģ«
    -0.94
    hesda
    -0.83
    FML
    -0.77
    ailability
    -0.74
    htar
    -0.72
    ForgeModLoader
    -0.70
    SPEC
    -0.67
    agara
    -0.66
    DEF
    -0.66
    POSITIVE LOGITS
     narration
    0.73
    ophon
    0.70
     omission
    0.69
     memoir
    0.67
     autobiography
    0.67
     screenplay
    0.66
     pus
    0.65
     memos
    0.65
    ruction
    0.64
     messenger
    0.64
    Activations Density 0.646%

    No Known Activations