INDEX

Explanations

commands and suggestions related to actions 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 @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

GraphicsUnit

-0.68

 Administrativna

-0.67

OGND

-0.63

abestanden

-0.63

Према

-0.62

GEBURTSDATUM

-0.61

 تانيه

-0.60

宜しくお願い

-0.60

correctly

-0.59

 corret

-0.58

POSITIVE LOGITS

 simply

0.85

 instead

0.84

 Instead

0.78

 alternatively

0.76

 consider

0.75

Instead

0.75

 einfach

0.75

try

0.74

干脆

0.70

ask

0.69

Activations Density 0.429%

commands and suggestions related to actions or instructions

No Comments

No Known Activations