INDEX

Explanations

references to locations, particularly cities and states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

identiality

-0.60

ANTLR

-0.57

 KUMAR

-0.56

 SINGH

-0.54

 setae

-0.53

➌

-0.53

complexContent

-0.53

valbard

-0.51

 onPage

-0.51

 vPvB

-0.51

POSITIVE LOGITS

 Detroit

1.13

 Chicago

1.12

 Boston

1.12

 Philadelphia

1.08

 Atlanta

1.06

 Seattle

1.04

Boston

1.02

Chicago

1.02

 Denver

1.01

APOLIS

1.01

Activations Density 0.187%

references to locations, particularly cities and states

No Comments

No Known Activations