INDEX

Explanations

variations of the prefix "ex" or words that start with "ex"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 numberOfRows

-0.88

mobileqq

-0.73

rlpool

-0.71

raisemb

-0.70

HtmlAttribute

-0.69

ToAction

-0.69

írus

-0.68

 reconno

-0.68

ppelin

-0.67

 LatLng

-0.66

POSITIVE LOGITS

ex

3.02

Ex

2.85

ex

2.81

Ex

2.76

EX

2.36

EX

2.18

exa

1.49

eks

1.43

exc

1.43

Exo

1.38

Activations Density 0.068%

variations of the prefix "ex" or words that start with "ex"

No Comments

No Known Activations