INDEX

Explanations

references to corners and intersections

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

databind

-0.91

 Réponses

-0.82

olesale

-0.81

hirts

-0.79

thansa

-0.79

tfrac

-0.79

írit

-0.78

icoot

-0.78

rália

-0.77

 Madsen

-0.76

POSITIVE LOGITS

 corner

2.47

 corners

2.30

 Corner

2.22

Corner

2.17

corner

2.15

 CORNER

2.07

 Corners

1.96

corners

1.89

Corners

1.82

 CORN

1.32

Activations Density 0.055%

references to corners and intersections

No Comments

No Known Activations