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. 11-RES-JB
    6. 19277
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations and management

    oai_token-act-pair · gpt-3.5-turbo

    key business-related concepts and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _-
    -0.70
     necks
    -0.67
    umbnails
    -0.66
     kidding
    -0.66
    jri
    -0.65
    Thumbnail
    -0.61
     inconvenient
    -0.61
    ourke
    -0.60
     retarded
    -0.59
     heads
    -0.59
    POSITIVE LOGITS
     SCP
    0.96
     EVE
    0.93
     Rune
    0.92
     Dynamo
    0.91
     Starg
    0.89
     Shroud
    0.88
     Hearthstone
    0.86
     Eclipse
    0.85
     Valiant
    0.85
     Compass
    0.82
    Activations Density 0.897%

    No Known Activations