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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 17573
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences expressing concern or worry

    oai_token-act-pair · gpt-3.5-turbo

    concerns or worries expressed about various subjects

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

    No Comments

    Negative Logits
    SPONSORED
    -0.93
    hesis
    -0.75
    ------------------------
    -0.74
    redits
    -0.70
    Written
    -0.70
    ammy
    -0.69
    gallery
    -0.69
    OGR
    -0.67
    hes
    -0.66
    waters
    -0.65
    POSITIVE LOGITS
     whether
    0.81
     getting
    0.79
     preventing
    0.77
     respecting
    0.74
     protecting
    0.74
     preserving
    0.74
     exposing
    0.73
     how
    0.72
     blowing
    0.71
     resolving
    0.71
    Activations Density 0.064%

    No Known Activations