© 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. 23787
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to abstract concepts such as senses, feelings, and perceptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate different aspects of perception or experience

    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
    sites
    -0.83
    ttes
    -0.80
    die
    -0.75
    nr
    -0.74
    esan
    -0.73
    iaries
    -0.72
    heid
    -0.70
    olicy
    -0.70
    ansas
    -0.70
    orst
    -0.70
    POSITIVE LOGITS
     urgency
    1.19
     humor
    0.95
     warmth
    0.94
     humour
    0.94
     nostalgia
    0.88
     insecurity
    0.88
     existential
    0.88
     optimism
    0.86
     parity
    0.84
     patriotism
    0.84
    Activations Density 0.077%

    No Known Activations