© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 4708
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cost" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to financial costs and expenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.77
     Beard
    -0.73
     Nether
    -0.72
    itialized
    -0.71
    unin
    -0.68
     DARK
    -0.68
    itles
    -0.66
    hirt
    -0.66
    itable
    -0.64
     Doodle
    -0.64
    POSITIVE LOGITS
    umed
    1.32
    liest
    1.24
    umers
    1.22
    lier
    1.17
     incurred
    1.09
    umer
    1.08
     overrun
    1.07
    umes
    1.00
    uming
    0.96
    anza
    0.93
    Activations Density 0.050%

    No Known Activations