INDEX

Explanations

specific brand names and product types related to technology and pharmaceuticals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Unburied

-0.72

 Kraw

-0.68

OGND

-0.68

tableFuture

-0.68

pidou

-0.68

Etr

-0.66

TRX

-0.65

 مشين

-0.64

herjee

-0.64

Jeho

-0.64

POSITIVE LOGITS

Nis

0.85

Nis

0.83

الدراسه

0.73

 Abra

0.73

 Chur

0.73

Lub

0.72

audrait

0.71

protoimpl

0.71

///</

0.70

 Rites

0.70

Activations Density 1.876%

specific brand names and product types related to technology and pharmaceuticals

No Comments

No Known Activations