INDEX

Explanations

numeric values indicating counts or scores related to data or feedback

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

]--;

-0.72

'],$

-0.69

webElementXpaths

-0.68

 المعيارى

-0.67

PerformLayout

-0.65

']")

-0.65

 CreateTagHelper

-0.65

 Réponses

-0.63

utnik

-0.63

 bezeichneter

-0.63

POSITIVE LOGITS

 textStatus

0.67

didReceive

0.60

 scorso

0.58

 blevet

0.57

 firebaseConfig

0.55

lma

0.53

ódó

0.53

 revanche

0.51

braun

0.51

 ogóle

0.50

Activations Density 0.054%

numeric values indicating counts or scores related to data or feedback

No Comments

No Known Activations