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. 8-RES-JB
    6. 9187
    Prev
    Next
    INDEX
    Explanations

    the word "Merc" or variations of the word like "Merciful" and "Merchantile"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Merc" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FORMATION
    -0.78
    gger
    -0.70
    åĤ
    -0.69
    ference
    -0.69
    mble
    -0.68
    Lay
    -0.68
    doors
    -0.68
    skirts
    -0.67
     DEBUG
    -0.65
     Ancients
    -0.64
    POSITIVE LOGITS
    iless
    1.32
    ifully
    1.23
    enaries
    1.20
    iful
    1.11
    uries
    1.00
    uria
    0.95
    ury
    0.94
    urious
    0.89
    enary
    0.89
    andise
    0.80
    Activations Density 0.043%

    No Known Activations