INDEX

Explanations

terms related to computer security policies and settings

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

StructEnd

-0.70

Tembelea

-0.65

 contextLoads

-0.64



-0.62

IndentedString

-0.60

extAlignment

-0.59

exitRule

-0.59

StoryboardSegue

-0.54

原始内容存档于

-0.53

badlogic

-0.52

POSITIVE LOGITS

 typelib

0.57

actionMode

0.49

\{

0.46

jsonwebtoken

0.46

évaluateur

0.45

CAB

0.45

@{

0.44

mof

0.44

سب

0.44

 hive

0.43

Activations Density 0.518%

terms related to computer security policies and settings

No Comments

No Known Activations