INDEX

Explanations

references to mirrors and reflections in various contexts, often relating to self-image or perceptions

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

]));

-0.54

geschlossen

-0.50

lieu

-0.50

`,

-0.50

 "));

-0.49

?";

-0.49

ruff

-0.49

enment

-0.49

")));

-0.48

今から

-0.48

POSITIVE LOGITS

Mirrors

1.15

 Mirrors

1.15

 mirror

1.12

 Mirror

1.11

 mirrors

1.10

 espejo

0.99

Mirror

0.96

 miroir

0.96

 MIRROR

0.95

 specchio

0.95

Activations Density 0.287%

references to mirrors and reflections in various contexts, often relating to self-image or perceptions

No Comments

No Known Activations