© 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. 2280
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies and initiatives aiming to improve services and efficiency across different sectors

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social equity and empowerment policies

    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
     FUCK
    -0.70
     fame
    -0.68
    Fest
    -0.65
     booze
    -0.64
    Joined
    -0.64
     shit
    -0.63
     piss
    -0.63
     rapper
    -0.62
     toast
    -0.62
     Weird
    -0.62
    POSITIVE LOGITS
     mechanisms
    0.90
     safeguards
    0.87
    effic
    0.86
     uncertainties
    0.83
     frameworks
    0.82
     Appropri
    0.80
     interventions
    0.79
     determin
    0.79
     discretionary
    0.78
     mitigation
    0.77
    Activations Density 1.046%

    No Known Activations