INDEX

Explanations

references to reading materials and online resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

RenderAtEndOf

-0.77

ConstraintMaker

-0.77

+#+#

-0.74

CGRectMake

-0.64

ForRow

-0.63

 BoxFit

-0.62

__":

-0.61

MemoryWarning

-0.61

CodeAttribute

-0.60

(;;

-0.59

POSITIVE LOGITS

ebay

0.77

 Google

0.75

 YouTube

0.74

twimg

0.74

 google

0.73

google

0.73

 Yelp

0.73

 Amazon

0.72

amazon

0.70

 LinkedIn

0.69

Activations Density 0.318%

references to reading materials and online resources

No Comments

No Known Activations