INDEX

Explanations

references to standards, particularly in legal and medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

حياته

-0.67

RTEE

-0.67

дельник

-0.55

 âgées

-0.54

reiches

-0.52

 mão

-0.52

AdapterFactory

-0.52

hirt

-0.51

förs

-0.51

 huvud

-0.50

POSITIVE LOGITS

 standards

1.71

standards

1.48

 Standards

1.47

Standards

1.39

 STANDARDS

1.39

 benchmarks

1.23

 standard

1.17

 benchmark

1.12

 STANDARD

1.12

 standart

1.12

Activations Density 0.637%

references to standards, particularly in legal and medical contexts

No Comments

No Known Activations