INDEX

Explanations

terms related to health and medical supplements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 dataSnapshot

-0.70

 betweenstory

-0.58

aarrggbb

-0.57

 kaynağından

-0.54

InitVars

-0.53

 astore

-0.52

AnchorTagHelper

-0.52

Rib

-0.52

 oprot

-0.52

principalTable

-0.52

POSITIVE LOGITS

tvguidetime

0.86

 himſelf

0.76

ſelf

0.74

 myſelf

0.72

 EconPapers

0.71

 Monfieur

0.71

 Majefty

0.70

 themſelves

0.68

 Universitaria

0.65

Datuak

0.64

Activations Density 0.413%

terms related to health and medical supplements

No Comments

No Known Activations