INDEX

Explanations

terms related to system security and permission settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

niosek

-0.66

dotti

-0.59

willReturn

-0.57

unnitel

-0.56

 fermés

-0.54

oarece

-0.54

 musikk

-0.54

 snabbt

-0.54

 hands

-0.53

SES

-0.53

POSITIVE LOGITS

3.90

1.35

1.20

1.02

0.97

tagHelperRunner

0.86

0.82

AndEndTag

0.77

脚注の使い方

0.75

protoimpl

0.75

Activations Density 0.009%

terms related to system security and permission settings

No Comments

No Known Activations