INDEX

Explanations

specific terminology and concepts related to biology and medical science

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<table>

-0.47

šanu

-0.46

〒

-0.45

hbase

-0.44

 equilibr

-0.44

êche

-0.44

Diwedd

-0.43

astify

-0.42

Portály

-0.42

_{\

-0.42

POSITIVE LOGITS

ité

1.08

itat

1.07

ITY

1.02

ITA

0.98

itere

0.96

itate

0.94

ITER

0.93

ità

0.92

########.

0.91

iter

0.91

Activations Density 2.352%

specific terminology and concepts related to biology and medical science

No Comments

No Known Activations