© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 19126
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and future events

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berman
    -0.70
     reproduce
    -0.68
    cloth
    -0.64
    lime
    -0.64
    ben
    -0.59
     besides
    -0.58
    cake
    -0.58
     countered
    -0.58
    hatt
    -0.58
     survives
    -0.58
    POSITIVE LOGITS
     latter
    0.95
     same
    0.94
     latest
    0.88
     entirety
    0.88
     Gulf
    0.85
     continent
    0.84
     west
    0.82
     autumn
    0.82
     foreseeable
    0.81
     earliest
    0.80
    Activations Density 0.538%

    No Known Activations