INDEX

Explanations

references to geographic features, particularly rivers and lakes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

пло

-0.44

[]

-0.42

 espal

-0.42

-0.41

or

-0.41

wanan

-0.40

-0.39

POSITIVE LOGITS

 rivers

1.34

 fleuve

1.20

 river

1.19

 rivière

1.15

 RIVER

1.10

 Streams

1.09

 River

1.08

River

1.08

 fiume

1.07

 streams

1.07

Activations Density 0.504%

references to geographic features, particularly rivers and lakes

No Comments

No Known Activations