INDEX

Explanations

occurrences of the letter "m" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Correia

-0.82

════════

-0.78

“

-0.77

“

-0.75

Pare

-0.71

ึ่ง

-0.70

-0.69

ígen

-0.69

 repar

-0.68

 Pare

-0.66

POSITIVE LOGITS

1.28

getM

1.25

1.22

 getM

1.19

1.17

0.99

 Alam

0.88

Amm

0.86

 mList

0.86

 &___

0.86

Activations Density 0.202%

occurrences of the letter "m" in various contexts

No Comments

No Known Activations