INDEX

Explanations

scientific terminology related to pharmaceuticals and medical treatments

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

able

-1.22

ability

-0.82

ization

-0.80

eyes

-0.78

ities

-0.76

epar

-0.75

ever

-0.75

HOLDER

-0.75

holders

-0.75

abetes

-0.74

POSITIVE LOGITS

est

0.53

es

0.51

ort

0.50

ة

0.45

athl

0.45

hes

0.44

ora

0.42

0.41

ests

0.41

esi

0.41

Activations Density 0.569%

scientific terminology related to pharmaceuticals and medical treatments

No Comments

No Known Activations