INDEX

Explanations

words related to medical terms in a specific language

oai_token-act-pair · gpt-3.5-turbo

the character 'ĥ' or variations thereof in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 contrace

-0.77

 mathemat

-0.76

quished

-0.75

espie

-0.74

owler

-0.72

 aspir

-0.71

iage

-0.70

 Sparkle

-0.69

idges

-0.69

bies

-0.68

POSITIVE LOGITS

ÏĦ

1.15

ï¸ı

1.04

ĥ

1.01

Îµ

0.96

Î¿

0.94

Îº

0.94

½

0.93

é¾įåĸļå£«

0.91

Ùħ

0.91

Î¹

0.90

Activations Density 0.007%

words related to medical terms in a specific language

the character 'ĥ' or variations thereof in different contexts

No Comments

No Known Activations