© 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. 2-RES-JB
    11. 3588
    Prev
    Next
    INDEX
    Explanations

    words related to rules, instructions, or commands

    oai_token-act-pair · gpt-3.5-turbo

    mentions of directives or regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Alto
    -0.79
     Argon
    -0.77
    ITE
    -0.77
    ock
    -0.76
     Blacks
    -0.74
    van
    -0.74
    Gordon
    -0.69
    OWS
    -0.69
     Sack
    -0.68
     Pens
    -0.68
    POSITIVE LOGITS
     directives
    1.24
     directive
    1.17
     confir
    0.93
     Directive
    0.88
     guiActiveUn
    0.87
     nod
    0.85
     decree
    0.84
     ordering
    0.83
     nomine
    0.83
     directs
    0.81
    Activations Density 0.007%

    No Known Activations