Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 20781
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaborating or working together

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and logical connectors in sentences

    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
    :[
    -0.82
    odore
    -0.77
    aterasu
    -0.75
    iencies
    -0.73
    etsk
    -0.70
    Downloadha
    -0.70
    imilar
    -0.68
    ©¶æ¥µ
    -0.66
    isks
    -0.66
    ï¸
    -0.64
    POSITIVE LOGITS
     spectator
    0.87
    sonian
    0.83
     limb
    0.80
     rider
    0.73
     litter
    0.72
     nationality
    0.70
     foot
    0.70
     metre
    0.69
     pound
    0.68
     messenger
    0.67
    Activations Density 0.358%

    No Known Activations