INDEX

Explanations

capitalized words or abbreviations likely related to technical terms or industries

oai_token-act-pair · gpt-3.5-turbo

variations of the letter 'v'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĪĴ

-0.78

¿½

-0.78

©¶æ

-0.72

ĨĴ

-0.72

Ú

-0.71

¥µ

-0.71

 millenn

-0.67

--------------------------------------------------------

-0.66

Ĥª

-0.64

Ô

-0.62

POSITIVE LOGITS

ascular

1.10

ests

1.04

ancouver

1.00

apor

0.96

olution

0.95

alkyrie

0.95

isible

0.94

ault

0.92

rolet

0.92

ideos

0.91

Activations Density 0.049%

capitalized words or abbreviations likely related to technical terms or industries

variations of the letter 'v'

No Comments

No Known Activations