INDEX

Explanations

terms and concepts related to biology and life sciences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ſelf

-0.98

bibinfo

-0.93

BibitemShut

-0.93

 Anſ

-0.90

Eſ

-0.88

 Inſ

-0.86

ſelves

-0.85

bibfield

-0.84

 purpoſe

-0.82

 iſt

-0.81

POSITIVE LOGITS

ar

0.76

]")]

0.72

[toxicity=0]

0.69

il

0.69

as

0.68

us

0.68

al

0.68

er

0.67

es

0.67

ak

0.67

Activations Density 3.932%

terms and concepts related to biology and life sciences

No Comments

No Known Activations