INDEX

Explanations

phrases discussing the impact of various factors

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

impact of or impact on

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

étoit

-0.54

 zijne

-0.53

 vertrouwen

-0.50

 jongen

-0.49

 ibunya

-0.48

 cervello

-0.46

 mówią

-0.44

 enfans

-0.41

 cewek

-0.39

 overeen

-0.39

POSITIVE LOGITS

 Impact

1.47

 impact

1.45

Impact

1.45

 IMPACT

1.38

impact

1.35

IMPACT

1.30

 impacts

1.20

 Impacts

1.12

 impacted

1.09

Impacts

1.09

Activations Density 0.012%

phrases discussing the impact of various factors

impact of or impact on

No Comments

No Known Activations