INDEX

Explanations

personal pronouns indicating relationships and social interactions

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

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

τέλε

-0.55

toned

-0.55

Something

-0.52

 something

-0.52

świ

-0.51

 Something

-0.50

 disposition

-0.50

ÍAS

-0.49

titleMargin

-0.49

 result

-0.48

POSITIVE LOGITS

 nakalista

0.84

 AssemblyCompany

0.75

devamını

0.64

 policiales

0.63

 ComVisible

0.61

 venons

0.60

 Autorizaciones

0.59

efois

0.58

 Arhivirano

0.58

principalColumn

0.57

Activations Density 0.098%

personal pronouns indicating relationships and social interactions

No Comments

No Known Activations