© 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. 8-RES-JB
    11. 6983
    Prev
    Next
    INDEX
    Explanations

    verbs related to providing assistance or support

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate forms of support and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GMT
    -0.86
    ulhu
    -0.76
    士
    -0.76
     Vortex
    -0.72
    é»Ĵ
    -0.69
    sonian
    -0.67
    isphere
    -0.66
     Linear
    -0.65
     skulls
    -0.63
     Inferno
    -0.63
    POSITIVE LOGITS
     encouragement
    1.01
     counsel
    1.00
     assisting
    0.99
     assist
    0.97
     supportive
    0.96
     aid
    0.93
     assistance
    0.91
     caring
    0.89
     compassionate
    0.89
     ally
    0.88
    Activations Density 0.363%

    No Known Activations