INDEX

Explanations

terms related to coding or programming, particularly in the context of URL or file references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 absch

-0.57

oredCriteria

-0.55

 TextAlign

-0.53

 توج

-0.51

canestro

-0.50

 goût

-0.48

हरा

-0.47

bidities

-0.47

 TabLayout

-0.47

XtraBars

-0.46

POSITIVE LOGITS

ts

1.28

 resourceCulture

0.79

bootstrapcdn

0.75

0.71

 فريبيس

0.66

 Fundamental

0.65

 Khart

0.65

AndEndTag

0.65

extends

0.64

ts

0.64

Activations Density 0.062%

terms related to coding or programming, particularly in the context of URL or file references

No Comments

No Known Activations