INDEX

Explanations

terms related to medical conditions or diseases

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

 oprot

-0.64

:✨

-0.63

InjectAttribute

-0.63

WriteTagHelper

-0.62

 namanya

-0.61

 poveznice

-0.60

 tillegg

-0.60

 propOrder

-0.60

værende

-0.60

 jScrollPane

-0.60

POSITIVE LOGITS

DR

1.45

DR

1.44

dr

1.24

dr

1.02

Dra

0.88

dri

0.81

Dra

0.80

dra

0.77

dra

0.76

Dri

0.74

Activations Density 0.051%

terms related to medical conditions or diseases

No Comments

No Known Activations