INDEX

Explanations

numerical data and values in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Two

-0.47

Two

-0.44

two

-0.42

 femmin

-0.42

Deux

-0.42

 Etter

-0.41

 houd

-0.40

 inherit

-0.39

 görüş

-0.39

 Hobson

-0.39

POSITIVE LOGITS

.*")]

0.90

principalTable

0.77

AddTagHelper

0.70

RTEE

0.68

SerializedName

0.63

InstanceState

0.63

ongyang

0.61

клопе

0.61

onAttach

0.60

---*/

0.60

Activations Density 0.242%

numerical data and values in various contexts

No Comments

No Known Activations