INDEX

Explanations

phrases indicating likelihood or estimation about choices and preferences

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

-0.44

 있어

-0.44

anto

-0.44

ваются

-0.43

DA

-0.42

da

-0.40

by

-0.40

mal

-0.40

da

-0.39

POSITIVE LOGITS

 oprot

1.00

likely

0.99

RectangleBorder

0.98

 Likely

0.97

outState

0.96

 likely

0.93

Likely

0.93

EndInit

0.92

GEBURTSDATUM

0.90

ContentAsync

0.89

Activations Density 0.288%

phrases indicating likelihood or estimation about choices and preferences

No Comments

No Known Activations