INDEX

Explanations

instances of the word "result" and related variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

viously

-0.75

 Wachs

-0.72

ENSES

-0.71

ionage

-0.71

Kav

-0.69

Eyed

-0.67

XmlAttribute

-0.66

monių

-0.66

 DELLE

-0.65

tokenize

-0.65

POSITIVE LOGITS

 results

1.55

 result

1.49

 Results

1.33

 Result

1.31

result

1.30

 RESULT

1.28

Result

1.27

Results

1.27

results

1.23

RESULT

1.17

Activations Density 0.119%

instances of the word "result" and related variations in different contexts

No Comments

No Known Activations