INDEX

Explanations

words related to "inside" and "outside"

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

 EconPapers

-0.69

 Falun

-0.58

ntlet

-0.57

ative

-0.57

nological

-0.57

helf

-0.56

ATIVE

-0.55

Datuak

-0.54

াহ

-0.53



-0.53

POSITIVE LOGITS

OUTSIDE

0.85

 Outside

0.84

outside

0.82

 OUTSIDE

0.81

Outside

0.80

inside

0.75

 Inside

0.70

Inside

0.70

INSIDE

0.69

 INSIDE

0.68

Activations Density 0.071%

words related to "inside" and "outside"

No Comments

No Known Activations