Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 18882
    Prev
    Next
    INDEX
    Explanations

    economic and financial hardships related to debt, costs, wages, working conditions, and standards of living

    oai_token-act-pair · gpt-3.5-turbo

    financial challenges and socioeconomic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atorium
    -0.65
     FANTASY
    -0.62
     coord
    -0.61
    ecast
    -0.60
     GOODMAN
    -0.60
    utherford
    -0.59
    adier
    -0.59
    ":"/
    -0.59
    vet
    -0.58
    ichick
    -0.58
    POSITIVE LOGITS
     ruining
    1.13
     compounded
    1.11
     exacerbated
    1.11
     plag
    1.09
     plagued
    1.07
     resulting
    1.06
     coupled
    0.98
    due
    0.98
     rife
    0.98
     hampered
    0.96
    Activations Density 0.565%

    No Known Activations