© 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. 2-RES-JB
    11. 8304
    Prev
    Next
    INDEX
    Explanations

    words related to aspirations or strong desires for achievement

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avis
    -0.77
    Pass
    -0.72
    eor
    -0.70
    EVA
    -0.68
    Surv
    -0.66
    ivan
    -0.65
    bah
    -0.65
    Veter
    -0.64
    said
    -0.64
    Person
    -0.63
    POSITIVE LOGITS
     ambitions
    1.12
     ambition
    1.10
     aspirations
    1.01
     aspiration
    0.94
     challeng
    0.90
    reprene
    0.80
     attainment
    0.79
    mares
    0.76
     aspire
    0.75
     ambitious
    0.75
    Activations Density 0.014%

    No Known Activations