INDEX

Explanations

references to medical studies and clinical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

NUMX

-0.84

tagHelperRunner

-0.80

ſelf

-0.79

 purpoſe

-0.77

ſelves

-0.73

 itſelf

-0.71

 pleaſure

-0.69

 Majefty

-0.66

 reaſon

-0.63

 fubject

-0.63

POSITIVE LOGITS

 parseFrom

0.60

 发表于

0.56

pfung

0.51

ścic

0.50

flashdata

0.50

gouv

0.47

发表于

0.46

 سكانية

0.45

parseFrom

0.45

readlines

0.44

Activations Density 0.703%

references to medical studies and clinical data

No Comments

No Known Activations