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. 9-RES-JB
    6. 10336
    Prev
    Next
    INDEX
    Explanations

    verb phrases suggesting strong endorsement or promotion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "touted" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matter
    -0.74
    erent
    -0.66
     context
    -0.65
    Ñı
    -0.65
    fur
    -0.63
    je
    -0.63
    Topic
    -0.61
     interfere
    -0.59
     unfocusedRange
    -0.58
    abus
    -0.57
    POSITIVE LOGITS
     virtues
    1.38
     successes
    1.23
     accomplishments
    1.07
     victories
    1.00
     accomplishment
    1.00
     achievements
    0.99
     superiority
    0.96
     success
    0.94
     victory
    0.92
    success
    0.89
    Activations Density 0.521%

    No Known Activations