INDEX

Explanations

language indicating assurance or certainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

enumi

-0.64

ho

-0.56

velle

-0.53

Als

-0.53

 pretend

-0.53

middot

-0.52

enumii

-0.51

Talk

-0.51

Ho

-0.50

 Simple

-0.50

POSITIVE LOGITS

 certainty

1.08

 guaranteed

0.93

 surety

0.88

tainty

0.88

 certitude

0.87

 guarantee

0.86

 definite

0.83

 незавершена

0.81

certainty

0.81

 Guaranteed

0.80

Activations Density 0.353%

language indicating assurance or certainty

No Comments

No Known Activations