INDEX

Explanations

conditional statements and modal verbs reflecting hypothetical situations

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

 myſelf

-1.33

 Majefty

-1.27

 fevere

-1.22

 feroit

-1.17

 Theſe

-1.17

 Monfieur

-1.14

 itſelf

-1.14

 pleaſure

-1.13

Efq

-1.11

 avoient

-1.10

POSITIVE LOGITS

↵↵

0.69

0.68

0.66

de

0.66

0.65

“

0.64

Activations Density 0.161%

conditional statements and modal verbs reflecting hypothetical situations

No Comments

No Known Activations