INDEX

Explanations

geographical locations and names associated with places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itoba

-0.53

Naw

-0.50

 cresc

-0.49

ISB

-0.44

 Waco

-0.44

springframework

-0.43

tahui

-0.43

nestjs

-0.42

Winnipeg

-0.41

Gag

-0.41

POSITIVE LOGITS

 Vermont

0.85

 Champlain

0.77

Vt

0.76

+#+#

0.75

Vermont

0.75

 Adirond

0.72

VT

0.70

 Saratoga

0.70

protoimpl

0.69

 Rens

0.67

Activations Density 0.127%

geographical locations and names associated with places

No Comments

No Known Activations