INDEX

Explanations

strings related to images and their attributes

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tanleria

-0.68

 ſche

-0.61

 Houſe

-0.60



-0.60

 AssemblyCulture

-0.60

 pleaſure

-0.60

 ſtate

-0.59

providedIn

-0.59

 GetEnumerator

-0.59

wiſe

-0.59

POSITIVE LOGITS

 afbeelding

0.36

 мәкал

0.35

 mijne

0.34

 rolled

0.34

 zijne

0.34

 helft

0.32

 decoração

0.30

 collezione

0.30

 aesthetically

0.29

 subido

0.29

Activations Density 0.012%

strings related to images and their attributes

No Comments

No Known Activations