INDEX

Explanations

terms related to scientific processes and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

-0.67

 المعيارى

-0.61

<bos>

-0.60

«

-0.59

...

-0.57

↵

-0.56

-0.54

-0.53

Enllaces

-0.51

le

-0.50

POSITIVE LOGITS

Efq

0.94

 Theſe

0.91

 Jefus

0.90

 Reſ

0.90

 myſelf

0.90

 ExecuteAsync

0.89

Eſ

0.89

 ſche

0.89

 Houſe

0.87

 doubtnut

0.87

Activations Density 0.778%

terms related to scientific processes and analysis

No Comments

No Known Activations