© 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. 6-RES-JB
    11. 765
    Prev
    Next
    INDEX
    Explanations

    references to the word "Cam" followed by a single character or another word

    oai_token-act-pair · gpt-3.5-turbo

    references to "Cam" or variations of that name

    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
    ãģį
    -0.81
     nomine
    -0.73
    Magikarp
    -0.71
     enriched
    -0.70
    hips
    -0.69
    lift
    -0.67
     disadvant
    -0.67
     prevail
    -0.65
     margins
    -0.65
    UCT
    -0.64
    POSITIVE LOGITS
    oufl
    1.39
    illus
    1.01
    aign
    0.97
    illa
    0.96
    elia
    0.93
    illas
    0.91
    ERA
    0.90
    ming
    0.88
    illo
    0.86
    ille
    0.86
    Activations Density 0.015%

    No Known Activations