INDEX

Explanations

references to identity and transformation concepts

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

bias

-0.55

treat

-0.53

Bias

-0.51

quo

-0.50

 iprot

-0.49

PLEMENT

-0.49

 fédéral

-0.48

èvement

-0.48

]})

-0.48

zeciw

-0.48

POSITIVE LOGITS

 cloned

0.67

 identity

0.66

 imposter

0.65

cloned

0.64

 Identität

0.64

 impostor

0.62

 Identity

0.61

 TextAppearance

0.59

 identidad

0.58

Identity

0.58

Activations Density 0.436%

references to identity and transformation concepts

No Comments

No Known Activations