INDEX

Explanations

references to specific places or events related to historical or educational significance

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

ing

-0.82

 Sanderson

-0.75

nd

-0.71

 Holliday

-0.71

 Πολ

-0.71

ction

-0.69

ation

-0.69

 Andree

-0.68

sion

-0.66

 Maier

-0.66

POSITIVE LOGITS

Lij

1.01

CWE

0.95

Yad

0.90

toDo

0.89

."</

0.89

 Nath

0.88

Nye

0.85

ulkner

0.83

reathable

0.82

XK

0.81

Activations Density 0.000%

references to specific places or events related to historical or educational significance

No Comments

No Known Activations