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. 10-RES-JB
    6. 18482
    Prev
    Next
    INDEX
    Explanations

    superlatives emphasizing extreme qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    the word "truly" and its variations, emphasizing authenticity or sincerity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newsletters
    -0.90
     Procedure
    -0.73
     Cheong
    -0.72
     Spray
    -0.69
    RY
    -0.68
    iewicz
    -0.67
    liners
    -0.66
    tones
    -0.66
    Posts
    -0.65
    also
    -0.64
    POSITIVE LOGITS
     appreciated
    0.84
     exceptional
    0.83
     deserving
    0.76
     altru
    0.74
     awe
    0.72
     unlimited
    0.72
     limitless
    0.72
     transformative
    0.71
     remarkable
    0.70
     astounding
    0.70
    Activations Density 0.032%

    No Known Activations