INDEX

Explanations

repeated occurrences of the word "For" indicating emphasis or topic transitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 MainAxisSize

-1.10

mybatisplus

-0.97

MemoryWarning

-0.94

featureID

-0.85

jsonwebtoken

-0.82

FTFY

-0.80

SpringRunner

-0.79

 ContentValues

-0.78

Kesimpulan

-0.76

randomUUID

-0.76

POSITIVE LOGITS

For

3.48

For

3.38

FOR

2.46

FOR

2.27

for

1.93

 Für

1.44

 Для

1.39

Для

1.35

Für

1.34

To

1.30

Activations Density 0.093%

repeated occurrences of the word "For" indicating emphasis or topic transitions

No Comments

No Known Activations