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. 6-RES-JB
    6. 2582
    Prev
    Next
    INDEX
    Explanations

    the name "Tim" with varying degrees of importance or relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Tim" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Magikarp
    -0.79
     traged
    -0.70
    Reloaded
    -0.67
    cffff
    -0.66
    avorite
    -0.64
    Untitled
    -0.64
     NETWORK
    -0.63
     discharge
    -0.63
     commissions
    -0.62
     poaching
    -0.62
    POSITIVE LOGITS
    estamp
    1.33
    othy
    1.19
    eless
    1.10
    mons
    1.05
    bre
    1.02
    my
    0.98
    mins
    0.96
     Ferr
    0.95
    elines
    0.91
    othe
    0.90
    Activations Density 0.020%

    No Known Activations