INDEX

Explanations

phrases related to values and ethical behavior in a digital context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 even

-0.51

RESET

-0.51

Externí

-0.48

 schauen

-0.47

inheritDoc

-0.46

 RESET

-0.46

jacency

-0.46

ografi

-0.45

omor

-0.44

 desperation

-0.44

POSITIVE LOGITS

ſelf

0.78

 Roskov

0.77

 שוליים

0.73

ſelves

0.73

 uſe

0.70

AddTagHelper

0.70

 purpoſe

0.69

 myſelf

0.68

Rptr

0.67

 auffi

0.67

Activations Density 0.262%

phrases related to values and ethical behavior in a digital context

No Comments

No Known Activations