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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8531
    Prev
    Next
    INDEX
    Explanations

    statements with "has been" followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    the verb "been," indicating actions or states that have occurred over time

    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
    terday
    -0.80
    rones
    -0.74
     Awakens
    -0.72
     Relief
    -0.69
    ives
    -0.69
    âĦ¢:
    -0.68
    Must
    -0.67
    lies
    -0.67
    odder
    -0.66
    would
    -0.66
    POSITIVE LOGITS
     subjected
    0.97
     likened
    0.96
     replaced
    0.94
     taken
    0.91
     shown
    0.90
    avering
    0.89
     deemed
    0.87
     criticized
    0.86
     seen
    0.85
     able
    0.84
    Activations Density 0.152%

    No Known Activations