INDEX

Explanations

segments related to informational content or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 resourceCulture

-1.09

 AssemblyVersion

-1.01

afficheront

-0.97

Personendaten

-0.92

KURZBESCHREIBUNG

-0.86

Попис

-0.85

 bezeichneter

-0.82

 виправивши

-0.81

évaluateur

-0.81

+#+#

-0.81

POSITIVE LOGITS

 more

0.56

詳

0.53

 details

0.51

詳しい

0.50

 current

0.48

 detailed

0.46

See

0.44

 full

0.43

Read

0.43

くわ

0.42

Activations Density 0.247%

segments related to informational content or instructions

No Comments

No Known Activations