INDEX

Explanations

negations and expressions of limitation or exclusion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 ſtill

-0.60

antaranya

-0.60

 ejus

-0.60

 vocale

-0.60

 itſelf

-0.58

 ſhe

-0.58

 tâche

-0.57

 onely

-0.55

 cité

-0.54

 quæ

-0.53

POSITIVE LOGITS

nor

0.72

 CURIAM

0.67

Nor

0.64

neither

0.62

 Wikimedijinoj

0.61

ConstraintMaker

0.61

 tampoco

0.61

GraphicsUnit

0.60

ρυ

0.60

Nor

0.59

Activations Density 0.221%

negations and expressions of limitation or exclusion

No Comments

No Known Activations

negations and expressions of limitation or exclusion

No Comments

No Known Activations