© 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. 3-RES-JB
    11. 1754
    Prev
    Next
    INDEX
    Explanations

    instances where the concept of cost is mentioned in relation to different scenarios

    oai_token-act-pair · gpt-3.5-turbo

    mentions of monetary cost and expenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.94
     Breed
    -0.76
    uberty
    -0.75
     Nether
    -0.74
    pload
    -0.73
    urtles
    -0.70
    gdala
    -0.70
    itialized
    -0.70
    unin
    -0.69
    odan
    -0.68
    POSITIVE LOGITS
    umed
    1.02
    liest
    0.99
    umers
    0.93
     prohib
    0.92
     incurred
    0.90
     overrun
    0.85
     reimbursement
    0.84
     taxpayers
    0.82
    lessly
    0.80
     savings
    0.80
    Activations Density 0.028%

    No Known Activations