INDEX

Explanations

instances of the word "found" and its variations, indicating discovery or realization

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

DataOutputStream

-0.87

yesha

-0.79

 Astor

-0.76

 Kirs

-0.75

 McIl

-0.75

 Maler

-0.75

 biotite

-0.74

uerung

-0.73

 Kahn

-0.72

 Baller

-0.72

POSITIVE LOGITS

 FIND

1.73

FIND

1.65

 Finds

1.64

 finds

1.64

 find

1.51

find

1.49

finds

1.44

 found

1.43

 Find

1.42

Find

1.42

Activations Density 0.139%

instances of the word "found" and its variations, indicating discovery or realization

No Comments

No Known Activations