INDEX

Explanations

verbs indicating actions, changes, or relationships in various contexts

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

actions and outcomes

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

was

-0.50

Â

-0.46

of

-0.40

<strong>

-0.38

 recently

-0.38

-0.37

cerpt

-0.37

Recently

-0.35

 Recently

-0.34

 lately

-0.33

POSITIVE LOGITS

pecabe

0.87

arangay

0.79

addCriterion

0.78

majánló

0.72

 ExecuteAsync

0.72

⤒

0.72

Rohy

0.72

 ſind

0.71

erintah

0.70

 increí

0.69

Activations Density 0.210%

verbs indicating actions, changes, or relationships in various contexts

actions and outcomes

No Comments

No Known Activations