© 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. 10-RES-JB
    11. 6655
    Prev
    Next
    INDEX
    Explanations

    references to items or concepts related to being inexpensive

    oai_token-act-pair · gpt-3.5-turbo

    references to affordability or low-cost options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ittees
    -0.78
    vironment
    -0.73
    ittee
    -0.70
    mbuds
    -0.70
    OHN
    -0.68
    jong
    -0.67
    iquette
    -0.67
    ADRA
    -0.66
    ¯
    -0.66
     skelet
    -0.66
    POSITIVE LOGITS
    liest
    1.07
    ened
    0.99
     priced
    0.95
    lier
    0.93
     rents
    0.85
    priced
    0.85
    Jet
    0.85
     cheap
    0.84
     labor
    0.83
    ered
    0.83
    Activations Density 0.047%

    No Known Activations