INDEX

Explanations

technical terminology related to research funding and acknowledgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Ladd

-0.52

%=

-0.49

lankton

-0.48

numerusform

-0.47

 Beecher

-0.45

WriteBarrier

-0.45

 OkHttpClient

-0.44

[]:

-0.44

 OSError

-0.44

ônus

-0.44

POSITIVE LOGITS

SourceChecksum

0.60

Viitteet

0.58

#+#

0.55

httphttps

0.55

 promo

0.52

Che

0.51

 Metzger

0.51

 engag

0.49

 Chef

0.48

 disambiguazione

0.48

Activations Density 0.067%

technical terminology related to research funding and acknowledgments

No Comments

No Known Activations