INDEX

Explanations

terms related to legal agreements and privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

IBOutlet

-0.55

 Paglinawan

-0.51

 وتسجيلات

-0.50

elemField

-0.45

LabelTagHelper

-0.45

AddTagHelper

-0.44

outState

-0.43

nextProps

-0.42

CardHeader

-0.42

arrings

-0.41

POSITIVE LOGITS

 Terms

0.58

Terms

0.53

 terms

0.53

 TERMS

0.52

terms

0.48

TERMS

0.47

ungsbedingungen

0.44

privacy

0.43

Policy

0.40

 privacy

0.40

Activations Density 0.329%

terms related to legal agreements and privacy policies

No Comments

No Known Activations