INDEX

Explanations

numerical values related to scores or outcomes in competitive events

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

 gynhyrchwyd

-0.66

IGENCE

-0.64

AddTagHelper

-0.64

 protoimpl

-0.63

UnifiedTopology

-0.62

VersionUID

-0.61

RetentionPolicy

-0.60

 NSCoder

-0.59

 skimage

-0.59

'];?>

-0.58

POSITIVE LOGITS

 >=",

0.64

 <<<<<<<<<<<<<<

0.58

 bronce

0.54

">//

0.54

↵↵

0.53

RegressionTest

0.50

 Good

0.48

êques

0.48

writeFieldEnd

0.47

twimg

0.46

Activations Density 0.151%

numerical values related to scores or outcomes in competitive events

No Comments

No Known Activations