INDEX

Explanations

concepts related to metrics of stability and validity in scientific frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Damon

-0.67

βάλ

-0.67

Documented

-0.65

an

-0.64

odenal

-0.62

ulate

-0.59

axaca

-0.58

 domésticos

-0.58

 Rapid

-0.57

REGISTER

-0.56

POSITIVE LOGITS

teness

1.15

tility

1.10

ITY

1.05

ibility

1.03

icity

1.00

ctility

1.00

ALITY

0.98

 ujednoznacz

0.97

cency

0.96

dibility

0.96

Activations Density 0.503%

concepts related to metrics of stability and validity in scientific frameworks

No Comments

No Known Activations