INDEX

Explanations

technical terms and specific statistical or mathematical phrases related to causal inference and modeling

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tafel

-0.51

TestBed

-0.46

nodoc

-0.44

Occurred

-0.43

ngths

-0.42

 Newswire

-0.42

 chương

-0.42

hable

-0.42

splat

-0.42

POSITIVE LOGITS

 MainAxisSize

0.73

 AssemblyCulture

0.71

Diweddarwch

0.70

msgTypes

0.66

UIControlState

0.64

 myſelf

0.63

mergeFrom

0.62

AndEndTag

0.61

ArrowToggle

0.60

frå

0.59

Activations Density 1.319%

technical terms and specific statistical or mathematical phrases related to causal inference and modeling

No Comments

No Known Activations