INDEX

Explanations

structural elements or formatting details within documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

นั้น

-0.67

 justement

-0.63

 that

-0.62

 were

-0.60

那就是

-0.59

 weren

-0.58

 quoi

-0.54

 indeed

-0.52

 totiž

-0.51

<bos>

-0.51

POSITIVE LOGITS

 Includes

1.49

Includes

1.40

 Requires

1.28

Requires

1.23

 Contains

1.12

Must

1.11

Contains

1.08

 Must

1.07

Can

1.04

Has

1.00

Activations Density 0.408%

structural elements or formatting details within documents

No Comments

No Known Activations