INDEX

Explanations

terms related to stereotypes and social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

OGND

-0.42

ManagedBean

-0.39

 conclude

-0.39

.”

-0.37

ediakan

-0.37

 podendo

-0.35

});*/

-0.35

 weitere

-0.35

ที่จะ

-0.34

lösung

-0.34

POSITIVE LOGITS

tagHelperRunner

0.68

Personendaten

0.64

LLocation

0.60

:✨

0.57

MLLoader

0.57

extAlignment

0.56

AndEndTag

0.56

énario

0.52

protoimpl

0.52

basicConfig

0.51

Activations Density 0.015%

terms related to stereotypes and social interactions

No Comments

No Known Activations