INDEX

Explanations

assertions in code, indicating validation checks or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Montal

-0.93

bè

-0.79

 Kitz

-0.71

 Audiodateien

-0.71

 maxn

-0.68

 betweenstory

-0.68

 Finney

-0.68

 keyCode

-0.67

chengladbach

-0.66

lipop

-0.66

POSITIVE LOGITS

assert

1.42

cassert

1.41

 assert

1.25

 asserts

1.17

 asserted

1.05

 assertions

1.00

 asserting

0.98

 claims

0.97

 Claims

0.94

 Asser

0.90

Activations Density 0.071%

assertions in code, indicating validation checks or conditions

No Comments

No Known Activations