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. 14644
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of dilution or deterioration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dilution or weakening

    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
    */(
    -1.18
    DragonMagazine
    -0.93
    Crunch
    -0.78
     Enabled
    -0.76
     Butterfly
    -0.75
    foundation
    -0.72
    PsyNetMessage
    -0.72
    ItemTracker
    -0.69
    ICA
    -0.68
     Origin
    -0.67
    POSITIVE LOGITS
     dil
    1.35
    usional
    1.04
     diluted
    0.97
    terness
    0.83
    ancing
    0.82
    ution
    0.81
    merga
    0.78
     bleach
    0.78
    usion
    0.77
    utive
    0.75
    Activations Density 0.007%

    No Known Activations