INDEX

Explanations

repeated terms and references to keys in data structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 themſelves

-1.00

 ſeveral

-0.96

 againſt

-0.94

 Theſe

-0.93

 ―――――

-0.92

 raiſ

-0.91

 myſelf

-0.91

 himſelf

-0.90

ſelf

-0.89

 itſelf

-0.89

POSITIVE LOGITS

key

3.45

key

3.25

Key

3.03

Key

2.85

KEY

2.83

KEY

2.78

 keys

2.78

 Keys

2.39

keys

2.32

setKey

2.19

Activations Density 0.047%

repeated terms and references to keys in data structures

No Comments

No Known Activations