INDEX

Explanations

nouns and articles related to identity or personal relationships

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

ly

-0.50

how

-0.46

How

-0.45

후

-0.44

</i>

-0.43

HOW

-0.41

立

-0.40

itemize

-0.40

und

-0.40

 cuales

-0.39

POSITIVE LOGITS

AddTagHelper

1.15

 Infórmanos

1.08

 AssemblyCulture

1.05

 disambiguazione

0.98

TagHelper

0.96

IntoConstraints

0.95

הערות

0.89

دانشنامهٔ

0.89

MetaObject

0.89

TextHelper

0.86

Activations Density 0.446%

nouns and articles related to identity or personal relationships

No Comments

No Known Activations