INDEX

Explanations

structured lists or items in a written format

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

tvguidetime

-1.04

 المعيارى

-0.86

 GenerationType

-0.83

 AssemblyCulture

-0.81

NonQuery

-0.71

 JpaRepository

-0.71

 ويكيميديا

-0.70

 กรัม

-0.70

----</

-0.69

afone

-0.68

POSITIVE LOGITS

The

1.33

 There

1.28

The

1.24

There

1.22

 When

1.07

 Although

1.05

When

1.02

If

1.01

Although

0.98

If

0.94

Activations Density 0.229%

structured lists or items in a written format

No Comments

No Known Activations