© 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. 10312
    Prev
    Next
    INDEX
    Explanations

    mentions of financial costs or expenses

    oai_token-act-pair · gpt-3.5-turbo

    references to various costs and expenses related to different situations

    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
    vironment
    -0.83
     Breed
    -0.76
     Nether
    -0.75
    itialized
    -0.73
    mbuds
    -0.73
    urtles
    -0.71
    uberty
    -0.71
     BST
    -0.69
    £ı
    -0.69
     Beard
    -0.68
    POSITIVE LOGITS
    liest
    1.00
    umed
    1.00
     incurred
    0.95
     overrun
    0.89
    umers
    0.88
     prohib
    0.87
     savings
    0.84
     reimbursement
    0.81
    lier
    0.81
    anza
    0.80
    Activations Density 0.034%

    No Known Activations