© 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. 11-RES-JB
    11. 15705
    Prev
    Next
    INDEX
    Explanations

    mentions related to salary and pay

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary compensation or salary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GGGGGGGG
    -0.75
     constitu
    -0.73
    Untitled
    -0.69
     Uriel
    -0.68
    REDACTED
    -0.66
     SPR
    -0.66
    ————
    -0.65
     projecting
    -0.64
    FTWARE
    -0.61
     conclud
    -0.61
    POSITIVE LOGITS
    checks
    1.27
    wall
    1.26
    offs
    1.22
    roll
    1.21
    pal
    1.16
    outs
    1.13
    back
    1.10
    Scale
    1.07
    days
    1.01
    tm
    1.01
    Activations Density 0.032%

    No Known Activations