INDEX

Explanations

terms related to biomedicine and drug approval processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ities

-0.82

holders

-0.82

ization

-0.77

HOLDER

-0.77

holder

-0.74

ized

-0.70

izable

-0.70

ists

-0.68

hander

-0.67

POSITIVE LOGITS

est

0.59

tttt

0.55

ttt

0.54

ipt

0.49

ort

0.48

ests

0.48

escrit

0.48

0.47

 Gaut

0.47

ET

0.46

Activations Density 0.874%

terms related to biomedicine and drug approval processes

No Comments

No Known Activations