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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13452
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial independence

    oai_token-act-pair · gpt-3.5-turbo

    lists of items or entities

    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
    nih
    -0.79
    abolic
    -0.67
    vale
    -0.64
    num
    -0.63
    uana
    -0.63
    ģĸ
    -0.62
    caps
    -0.61
    ](
    -0.60
    ctx
    -0.59
    ole
    -0.59
    POSITIVE LOGITS
     meanwhile
    1.48
     huh
    1.14
     however
    1.05
     unsurprisingly
    0.87
     moreover
    0.87
     eh
    0.81
     incidentally
    0.80
     meantime
    0.79
     beware
    0.78
     rejoice
    0.77
    Activations Density 0.289%

    No Known Activations