INDEX

Explanations

content related to API authorization and token management

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

OAuth and similar authentication methods

np_acts-logits-general · gemini-2.0-flash

OAuth token

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Moseley

-0.50

verwijspagina

-0.48

发表于

-0.47

ciąg

-0.46

onion

-0.45

 unborn

-0.45

saraba

-0.44

 kast

-0.44

 Processors

-0.43

SizeF

-0.43

POSITIVE LOGITS

 OAuth

0.75

oauth

0.73

 oauth

0.71

 grant

0.67

NameInMap

0.67

 scopes

0.67

Grant

0.66

 Grant

0.65

grant

0.64

OAuth

0.64

Activations Density 0.220%

content related to API authorization and token management

OAuth and similar authentication methods

OAuth token

No Comments

No Known Activations