INDEX

Explanations

words related to a specific type of cell or scientific terminology

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

BibitemShut

-1.05

 ་་

-0.99

 Monfieur

-0.89

 mín

-0.88

 Satt

-0.88

BrowserModule

-0.86

CNP

-0.84

 myſelf

-0.83

 dand

-0.82

 mika

-0.82

POSITIVE LOGITS

ro

1.65

Ro

1.16

ro

1.13

Ro

1.00

RO

0.98

 Rovers

0.95

 Roch

0.85

RO

0.85

 Roper

0.84

iro

0.78

Activations Density 0.001%

words related to a specific type of cell or scientific terminology

No Comments

No Known Activations