INDEX

Explanations

references to API-related structures and protocols

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

"api" or "API" tokens

np_acts-logits-general · gemini-2.0-flash

API references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

hold

-0.41

over

-0.40

‘

-0.37

 Hough

-0.35

brought

-0.35

‘

-0.34

con

-0.34

<em>

-0.34

POSITIVE LOGITS

API

1.13

Api

1.07

api

1.05

 APIs

0.99

API

0.89

api

0.87

Api

0.87

 ApiService

0.86

CppMethod

0.84

APIs

0.83

Activations Density 0.188%

references to API-related structures and protocols

"api" or "API" tokens

API references

No Comments

No Known Activations