INDEX

Explanations

phrases related to warnings, claims, or assertions 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 @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 manches

-0.51

 Pingback

-0.48

 विश्वसनीयता

-0.46

 venit

-0.46

 telep

-0.45

 marrone

-0.45

 culturelles

-0.44

 bocca

-0.44

 publiques

-0.44

 kanya

-0.44

POSITIVE LOGITS

AddTagHelper

0.90

 Мексичка

0.70

ättä

0.69

 nakalista

0.65

]}"

0.64

!("{}",

0.64

 SwitchCompat

0.64

rrggbb

0.62

<?

0.62

 getItemCount

0.61

Activations Density 2.829%

phrases related to warnings, claims, or assertions within documents

No Comments

No Known Activations