INDEX

Explanations

phrases related to comparisons and evaluations between different options or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Obrázky

-0.56

 propOrder

-0.52

 ExecuteAsync

-0.51

nloa

-0.51

醐

-0.50

ⓧ

-0.48

ConstraintMaker

-0.48

brainly

-0.46

LICENSE

-0.46

phils

-0.45

POSITIVE LOGITS

 comparison

3.54

 comparisons

3.19

 compare

3.17

 Comparison

3.11

 comparing

3.07

comparison

3.00

 compares

2.93

Comparison

2.87

 comparaison

2.84

 Compare

2.84

Activations Density 0.885%

phrases related to comparisons and evaluations between different options or entities

No Comments

No Known Activations