© 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. 4-RES-JB
    11. 14898
    Prev
    Next
    INDEX
    Explanations

    mentions of items or services that are inexpensive or low-cost

    oai_token-act-pair · gpt-3.5-turbo

    references to low-cost items or experiences

    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
    uberty
    -0.83
    âĹ¼
    -0.83
    ittee
    -0.83
     skelet
    -0.76
    ittees
    -0.75
    vironment
    -0.75
    jong
    -0.75
     Disorder
    -0.73
    mbuds
    -0.70
    regon
    -0.69
    POSITIVE LOGITS
     cheap
    1.03
    ened
    1.02
    liest
    1.01
    eners
    0.86
    lier
    0.84
     inexpensive
    0.81
     enough
    0.79
     cheapest
    0.77
     cheaply
    0.77
     fares
    0.75
    Activations Density 0.016%

    No Known Activations