INDEX

Explanations

complex sentences involving multiple clauses or ideas

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-0.80

 zelve

-0.78

 myſelf

-0.77

 houſe

-0.76

 pleaſure

-0.74

 ſtill

-0.73

onekana

-0.73

 zijne

-0.73

 ſtate

-0.72

 ſon

-0.72

POSITIVE LOGITS

auf

0.75

GEBURTSDATUM

0.68

fe

0.61

abestanden

0.60

parsedMessage

0.60

 ProtoMessage

0.56

vor

0.56

aus

0.56

期刊论文

0.56

gew

0.55

Activations Density 0.059%

complex sentences involving multiple clauses or ideas

No Comments

No Known Activations

complex sentences involving multiple clauses or ideas

No Comments

No Known Activations