INDEX

Explanations

instances where the outcome or decision is in favor of a party or individual

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

orance

-0.53

avyzd

-0.52

üp

-0.50

aneously

-0.50

[]

-0.49

éal

-0.48

InSection

-0.48

 panne

-0.48

Schwe

-0.48

ього

-0.47

POSITIVE LOGITS

 favorable

0.80

 unfavorable

0.79

Fav

0.78

 favourable

0.78

 favour

0.78

 favor

0.77

 FAVOR

0.75

 favors

0.74

fav

0.73

 Favor

0.73

Activations Density 0.122%

instances where the outcome or decision is in favor of a party or individual

No Comments

No Known Activations