© 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. 2-RES-JB
    11. 1066
    Prev
    Next
    INDEX
    Explanations

    monetary values

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary values or costs associated with recurring payments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.77
     Ruk
    -0.71
    çĶ°
    -0.71
    enegger
    -0.69
    hound
    -0.68
    ORK
    -0.67
    ARDIS
    -0.66
    MpServer
    -0.64
    OHN
    -0.64
    姫
    -0.63
    POSITIVE LOGITS
     capita
    1.30
    malink
    1.00
    tains
    0.97
    ishable
    0.96
    mits
    0.91
    uvian
    0.87
    missible
    0.83
    verting
    0.81
    severe
    0.80
    missions
    0.80
    Activations Density 0.031%

    No Known Activations