INDEX

Explanations

references to maximum and minimum quantities or amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Sp

-0.64

tive

-0.61

 jette

-0.57

ソル

-0.57

col

-0.56

-0.55

jar

-0.55

б

-0.55

SP

-0.55

 puis

-0.55

POSITIVE LOGITS

MAXIMUM

1.51

maximum

1.48

 MAXIMUM

1.45

minimum

1.42

 maximum

1.42

 Maximum

1.41

Maximum

1.36

MINIMUM

1.34

Minimum

1.33

 Minimum

1.27

Activations Density 0.069%

references to maximum and minimum quantities or amounts

No Comments

No Known Activations