INDEX

Explanations

terms related to anti-drug or anti-agent concepts in medical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

expandindo

-0.82

 Roskov

-0.80

 estekak

-0.79

]}

-0.76

 CreateTagHelper

-0.75

OGND

-0.74

 utafitiHapana

-0.74

 OFDb

-0.70

 AssemblyCulture

-0.69

ftagPool

-0.69

POSITIVE LOGITS

 anti

1.04

 Anti

0.97

Anti

0.96

 ANTI

0.94

anti

0.78

ANTI

0.75

 Анти

0.74

 antig

0.72

Анти

0.71

 antis

0.71

Activations Density 0.096%

terms related to anti-drug or anti-agent concepts in medical contexts

No Comments

No Known Activations