INDEX

Explanations

structured data formats and patterns

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

 myſelf

-0.94

 anſ

-0.92

 pleaſure

-0.90

migrationBuilder

-0.89

 tranſ

-0.88

 purpoſe

-0.86

 deſt

-0.85

 leſs

-0.84

 perſon

-0.83

 فريبيس

-0.83

POSITIVE LOGITS

ESTAMP

0.60

 AssemblyTitle

0.52

ISupport

0.48

Dr

0.46

ticias

0.45

Mr

0.44

<eos>

0.44

Activations Density 0.258%

structured data formats and patterns

No Comments

No Known Activations