© 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. 1-RES-JB
    11. 11384
    Prev
    Next
    INDEX
    Explanations

    words related to sponsoring or endorsing something

    oai_token-act-pair · gpt-3.5-turbo

    references to sponsorship 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
     PCB
    -0.77
     ECB
    -0.72
     DG
    -0.69
     Guinness
    -0.69
     exit
    -0.67
     paddle
    -0.66
     reckoning
    -0.65
     pity
    -0.64
     circumcision
    -0.63
     Britann
    -0.63
    POSITIVE LOGITS
    orship
    1.22
    orial
    1.14
    ospons
    1.02
    spons
    1.01
    rum
    0.99
    align
    0.96
    ibilities
    0.93
    ory
    0.91
    or
    0.90
    ctr
    0.88
    Activations Density 0.014%

    No Known Activations