INDEX

Explanations

assertions of knowledge or understanding

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

 tartalomajánló

-0.93

__":

-0.81

prechpartner

-0.77

__':

-0.77

__":

-0.76

 المعيارى

-0.75

__':

-0.75

poons

-0.72

 lenker

-0.71

 referenties

-0.70

POSITIVE LOGITS

 wiem

0.58

 excuse

0.58

 conozco

0.56

 tudom

0.54

 excuses

0.53

我知道

0.52

 know

0.51

 muun

0.49

 knows

0.49

uage

0.47

Activations Density 0.109%

assertions of knowledge or understanding

No Comments

No Known Activations