INDEX

Explanations

words related to medical conditions or treatments, specifically focusing on 'warts'

oai_token-act-pair · gpt-3.5-turbo

occurrences or mentions of "arts."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ascus

-0.71

phis

-0.68

EStream

-0.68

è¦ļéĨĴ

-0.68

dayName

-0.67

 cumbers

-0.65

 occas

-0.64

berman

-0.62

pora

-0.62

PLIED

-0.62

POSITIVE LOGITS

arts

0.99

heid

0.98

ners

0.83

oon

0.83

ICLE

0.82

heet

0.80

oons

0.80

ending

0.77

esian

0.76

emis

0.76

Activations Density 0.007%

words related to medical conditions or treatments, specifically focusing on 'warts'

occurrences or mentions of "arts."

No Comments

No Known Activations