© 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. 10-RES-JB
    11. 2750
    Prev
    Next
    INDEX
    Explanations

    physical dimensions such as height, width, depth, and weight

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications or measurements related to physical objects

    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
    haps
    -0.82
    nesday
    -0.73
    endars
    -0.72
    assad
    -0.70
    leep
    -0.69
    irds
    -0.67
     reneg
    -0.67
    aroo
    -0.67
    humans
    -0.67
    xit
    -0.67
    POSITIVE LOGITS
     Width
    1.21
     diameter
    1.20
     circumference
    1.15
     thickness
    1.13
     height
    1.08
     Warranty
    1.07
     Height
    1.07
     Weight
    1.06
     Capacity
    1.06
     Dimensions
    1.06
    Activations Density 0.139%

    No Known Activations