INDEX

Explanations

instances of the word "strong" or similar terms emphasizing strength or intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enumi

-0.79

kaido

-0.78

upaten

-0.74

atimes

-0.73

 Maus

-0.69

 Miyazaki

-0.67

[]:

-0.67

AccessException

-0.66

Loot

-0.66

 oblivion

-0.65

POSITIVE LOGITS

STRONG

1.41

strong

1.41

 Strong

1.40

Strong

1.35

 STRONG

1.34

 strong

1.26

strength

1.25

ngths

1.15

 strength

1.15

Strength

1.14

Activations Density 0.089%

instances of the word "strong" or similar terms emphasizing strength or intensity

No Comments

No Known Activations