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. 10-RES-JB
    6. 13513
    Prev
    Next
    INDEX
    Explanations

    phrases related to the spatial positions of objects or points

    oai_token-act-pair · gpt-3.5-turbo

    phrases or references related to location or position

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dayName
    -0.68
    etic
    -0.66
    resy
    -0.64
    thren
    -0.62
    893
    -0.59
    forts
    -0.59
    ~~~~~~~~~~~~~~~~
    -0.58
    far
    -0.58
    ****************
    -0.57
    DEN
    -0.57
    POSITIVE LOGITS
     each
    0.86
     the
    0.84
     town
    0.78
     nowhere
    0.76
     stairs
    0.75
     campus
    0.70
    rium
    0.67
     every
    0.67
     chromosomes
    0.66
    course
    0.66
    Activations Density 0.111%

    No Known Activations