INDEX

Explanations

terms related to locking mechanisms and security

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.81

thâu

-0.63

 fantasmas

-0.61

äler

-0.61

berikut

-0.57

ESIS

-0.57

isateur

-0.57

oneph

-0.56

atitis

-0.55

hibli

-0.54

POSITIVE LOGITS

 Locks

1.26

Locks

1.23

 locks

1.16

 LOCK

1.04

 lock

1.00

 Lock

1.00

LOCK

0.99

locks

0.97

lock

0.91

 locking

0.89

Activations Density 0.068%

terms related to locking mechanisms and security

No Comments

No Known Activations