INDEX

Explanations

references to George W. Bush

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

 Shreve

-0.82

 nguyễn

-0.78

ransition

-0.77

atedral

-0.75

kler

-0.74

 McKinley

-0.74

avits

-0.73

ligators

-0.72

 Chall

-0.72

Jakub

-0.71

POSITIVE LOGITS

 George

2.21

George

1.99

george

1.80

 GEORGE

1.76

 george

1.70

GEORGE

1.59

 Georges

1.58

Georges

1.29

Geo

1.20

 Georgie

1.18

Activations Density 0.016%

references to George W. Bush

No Comments

No Known Activations