INDEX

Explanations

terms related to authentication and security processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

RetentionPolicy

-0.61

ništ

-0.54

JScrollPane

-0.54

出版年

-0.52

ennett

-0.50

jScrollPane

-0.50

 unloaded

-0.49

 Marxism

-0.49

 Salaries

-0.49

 surla

-0.48

POSITIVE LOGITS

 verification

1.41

 Verification

1.24

Verification

1.17

 verify

1.14

verification

1.12

 verifying

1.11

 confirmation

1.10

 Verify

1.08

Verify

1.02

VER

0.99

Activations Density 0.229%

terms related to authentication and security processes

No Comments

No Known Activations