© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 20095
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something that is required or cannot be avoided

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mandatory or compulsory actions and 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
     Indies
    -0.79
     Stam
    -0.78
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.70
    hner
    -0.68
    than
    -0.68
    ander
    -0.66
     Blessed
    -0.66
    agate
    -0.65
    bill
    -0.65
    ience
    -0.64
    POSITIVE LOGITS
     compulsory
    1.35
    avorite
    0.97
     redund
    0.93
     reluct
    0.92
    untarily
    0.91
     destro
    0.85
     confir
    0.84
     mandatory
    0.81
    untary
    0.80
     obligatory
    0.79
    Activations Density 0.007%

    No Known Activations