INDEX

Explanations

proper nouns, particularly names of people and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

$.

-0.97

intios

-0.94

"],

-0.93

"):

-0.90

'],

-0.87

EDEFAULT

-0.87

*/;

-0.86

."</

-0.85

".

-0.84

webElementXpaths

-0.83

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.60

0.54

ho

0.53

0.50

 asciug

0.49

res

0.48

ang

0.47

an

0.46

Activations Density 0.590%

proper nouns, particularly names of people and organizations

No Comments

No Known Activations