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. 11-RES-JB
    6. 23366
    Prev
    Next
    INDEX
    Explanations

    characteristics or components that are similar to each other, or actions that involve comparison

    oai_token-act-pair · gpt-3.5-turbo

    references to physical characteristics and properties of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WATCHED
    -0.63
     upro
    -0.61
    financial
    -0.60
    Progress
    -0.59
    erity
    -0.59
     contingent
    -0.59
    Change
    -0.59
     restructuring
    -0.58
     restruct
    -0.58
    comm
    -0.58
    POSITIVE LOGITS
     pictured
    1.01
     commonly
    0.98
     used
    0.92
     worn
    0.89
     normally
    0.87
     nowadays
    0.84
     seen
    0.84
     typical
    0.83
     Used
    0.80
     found
    0.80
    Activations Density 0.378%

    No Known Activations