INDEX

Explanations

expressions related to scoring or ratings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<eos>

-0.47

makedirs

-0.44

rowCount

-0.42

-0.41

 membahas

-0.41

là

-0.41

 kelebihan

-0.40

仔

-0.40

 mantequilla

-0.40

...

-0.39

POSITIVE LOGITS

 score

1.13

AnchorStyles

1.11

 ſind

0.91

Efq

0.90

 Score

0.89

 ―――――

0.89

 itſelf

0.87

score

0.86

SequentialGroup

0.84

Eſ

0.84

Activations Density 0.188%

expressions related to scoring or ratings in various contexts

No Comments

No Known Activations