INDEX

Explanations

instances of the letter 'a' 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 @ 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

 iſt

-0.99

 itſelf

-0.96

Personendaten

-0.92

ſy

-0.89

 myſelf

-0.89

 ―――――

-0.87

 ་་

-0.85

theless

-0.84

 pleaſure

-0.84

 ſeveral

-0.84

POSITIVE LOGITS

à

1.24

to

1.20

zu

0.94

к

0.89

 به

0.89

to

0.85

 προς

0.84

 unto

0.84

TO

0.84

To

0.81

Activations Density 0.037%

instances of the letter 'a' in various contexts

No Comments

No Known Activations