© 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. 1-RES-JB
    11. 24108
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing assistance or support

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "helping," indicating a focus on support and assistance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾
    -0.72
    Pict
    -0.70
     Purg
    -0.68
    Rum
    -0.64
    uns
    -0.62
    pora
    -0.61
    Policy
    -0.61
    archives
    -0.60
    gran
    -0.60
    nu
    -0.59
    POSITIVE LOGITS
     helping
    0.96
     Assist
    0.89
    oaded
    0.81
    soDeliveryDate
    0.79
     aid
    0.78
    igor
    0.77
     assisting
    0.76
    heet
    0.75
     facilitate
    0.74
     aids
    0.73
    Activations Density 0.009%

    No Known Activations