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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 7383
    Prev
    Next
    INDEX
    Explanations

    terms related to future plans or goals

    oai_token-act-pair · gpt-3.5-turbo

    references to ambitions and aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Correct
    -0.77
    Correct
    -0.77
     Correction
    -0.71
    ERAL
    -0.70
    fine
    -0.70
    correct
    -0.69
    fect
    -0.68
    ffect
    -0.67
     DOT
    -0.67
    aneous
    -0.67
    POSITIVE LOGITS
     ambition
    3.32
     ambitions
    3.18
     aspirations
    2.84
     aspiration
    2.18
     aspire
    1.71
     ambitious
    1.55
     aspir
    1.44
    bitious
    1.41
     dreams
    1.37
     hopes
    1.23
    Activations Density 0.015%

    No Known Activations