INDEX

Explanations

references to APIs and their versions

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

"api" or "API"

np_acts-logits-general · gemini-2.0-flash

api and request

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

contentLoaded

-0.48

hpur

-0.42

tan

-0.40

RTGC

-0.38

+#+#

-0.37

nott

-0.37

ment

-0.37

 RouterModule

-0.36

ljen

-0.36

dd

-0.35

POSITIVE LOGITS

Api

0.78

api

0.68

API

0.62

Api

0.56

 APIs

0.54

api

0.51

API

0.50

VIAF

0.49

 apiKey

0.45

 resourceCulture

0.45

Activations Density 0.092%

references to APIs and their versions

"api" or "API"

api and request

No Comments

No Known Activations