© 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. 3665
    Prev
    Next
    INDEX
    Explanations

    phrases related to being projected or forecasted to occur

    oai_token-act-pair · gpt-3.5-turbo

    references to "the" as a prominent article throughout the text

    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
    BIL
    -0.82
    LOCK
    -0.74
    LEASE
    -0.73
    RESULTS
    -0.68
    FIG
    -0.68
    èĢ
    -0.67
    EVA
    -0.67
    VPN
    -0.66
     whilst
    -0.66
    ocide
    -0.65
    POSITIVE LOGITS
     vicinity
    1.22
     periphery
    1.00
     midst
    0.95
     neighbourhood
    0.92
     same
    0.91
     countryside
    0.84
     country
    0.83
     slightest
    0.83
     neighborhood
    0.83
     middle
    0.83
    Activations Density 0.337%

    No Known Activations