INDEX

Explanations

negative implications or consequences of actions

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

aarrggbb

-1.05

 الحره

-0.92

 تضيفلها

-0.92

+#+#

-0.91

tvguidetime

-0.89

 متعلقه

-0.88

 linkovi

-0.86

verwijspagina

-0.85

 autorytatywna

-0.82

ReusableCell

-0.77

POSITIVE LOGITS

0.51

↵

0.45

0.44

/\.

0.42

 also

0.42

 batch

0.41

 nostru

0.41

 bromide

0.41

INARY

0.41

↵↵↵

0.41

Activations Density 0.010%

negative implications or consequences of actions

No Comments

No Known Activations