INDEX

Explanations

terms related to merging and publishing information, particularly in formal or legal 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

enapa

-0.57

curacies

-0.57

 htons

-0.54

lüssel

-0.53

ACHUSETTS

-0.53

gyar

-0.53

dimethy

-0.53

 vers

-0.53

🦱

-0.52

 terbuka

-0.52

POSITIVE LOGITS

Mer

1.56

Mer

1.53

mer

1.45

mer

1.39

MER

1.35

MER

1.18

merge

0.96

 Merge

0.95

Merge

0.95

 mers

0.89

Activations Density 1.635%

terms related to merging and publishing information, particularly in formal or legal contexts

No Comments

No Known Activations