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. 7-RES-JB
    6. 10155
    Prev
    Next
    INDEX
    Explanations

    references to completion or finalization

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'finishing' or 'completion'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uli
    -0.82
    hare
    -0.74
    elled
    -0.74
    edia
    -0.71
    orum
    -0.67
    ulated
    -0.67
    resy
    -0.66
    esis
    -0.65
    ourage
    -0.64
    ulation
    -0.64
    POSITIVE LOGITS
     touches
    0.89
     unfinished
    0.76
    teness
    0.68
     Exam
    0.67
     Finish
    0.67
     finishing
    0.64
     uninterrupted
    0.64
     preparations
    0.64
    housing
    0.64
    work
    0.64
    Activations Density 0.028%

    No Known Activations