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. 11-RES-JB
    6. 9608
    Prev
    Next
    INDEX
    Explanations

    instances where someone is recalling or reacting to new information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrases related to hearing and learning new information

    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
    ometimes
    -0.80
    except
    -0.75
    ccording
    -0.73
    umerous
    -0.72
     entirely
    -0.70
    unless
    -0.68
    COMPLE
    -0.67
     unparalleled
    -0.67
    aples
    -0.67
    actly
    -0.66
    POSITIVE LOGITS
     my
    0.67
     puberty
    0.61
     Wings
    0.59
     Deadline
    0.59
     this
    0.58
     Pist
    0.57
     goodbye
    0.57
     Sloan
    0.56
     Flower
    0.56
     graduation
    0.56
    Activations Density 0.252%

    No Known Activations