INDEX

Explanations

proper nouns and terms related to medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Barrow

-0.82

-0.79

Hud

-0.79

 Weih

-0.77

</i>

-0.74

Marlene

-0.72

zu

-0.71

 Rodrig

-0.71

 Marlene

-0.71

“

-0.71

POSITIVE LOGITS

 ArrayAdapter

0.99

 Jaffe

0.85

 Freuden

0.83

ArrayAdapter

0.83

omenclature

0.83

 Fick

0.81

 HttpNotFound

0.81

jectures

0.81

SDAY

0.80

 Lichten

0.79

Activations Density 0.395%

proper nouns and terms related to medical conditions

No Comments

No Known Activations