INDEX

Explanations

instances where the text indicates the beginning of a new section or notable event

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

StoryboardSegue

-0.55

RegressionTest

-0.51

fromnode

-0.50

DoubleQuotes

-0.49

 their

-0.47

The

-0.46

 صوتيه

-0.44

 quedarse

-0.44

 program

-0.43

who

-0.43

POSITIVE LOGITS

 myſelf

1.16

 initComponents

1.09

]")]

0.85

 Anſ

0.81

 purpoſe

0.79

 StringTokenizer

0.78

Efq

0.76

 Reſ

0.76

 nahilalakip

0.74

ſelf

0.74

Activations Density 0.156%

instances where the text indicates the beginning of a new section or notable event

No Comments

No Known Activations