INDEX

Explanations

segments of text that indicate the presence of specific scientific terms or concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-1.07

QMetaType

-1.04

WebElementEntity

-1.02

uxxxx

-0.93

 ModelExpression

-0.90

 propOrder

-0.87

PostInfinity

-0.84

IntoConstraints

-0.83

oredCriteria

-0.82

webElementXpaths

-0.81

POSITIVE LOGITS

0.60

↵↵

0.57

CrossRef

0.56

0.54

)]

0.46

publicain

0.46

ずつ

0.46

뿌

0.45

Boys

0.45

am

0.44

Activations Density 0.003%

segments of text that indicate the presence of specific scientific terms or concepts

No Comments

No Known Activations