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. 1-RES-JB
    6. 3815
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or obligation

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing necessities or obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hamp
    -0.70
     Junk
    -0.67
     Mur
    -0.65
     Pok
    -0.61
     Atmosp
    -0.61
    versions
    -0.61
     Marlins
    -0.59
     Vish
    -0.59
     Trophy
    -0.59
     Arena
    -0.59
    POSITIVE LOGITS
     obey
    1.01
     reproduce
    0.92
     surely
    0.84
     comply
    0.80
     conclud
    0.80
    %%%%
    0.80
     unavoid
    0.80
    must
    0.80
     be
    0.79
    Must
    0.79
    Activations Density 0.027%

    No Known Activations