INDEX

Explanations

DOI numbers

oai_token-act-pair · gpt-3.5-turbo

numerical data and references in the context of academic articles or scientific reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ļ½

-0.82

ï¸

-0.81

querque

-0.79

PDATE

-0.71

ipel

-0.68

ħĭ

-0.68

 Shogun

-0.64

 Triangle

-0.64

 Dominion

-0.64

¶æ

-0.63

POSITIVE LOGITS

0.93

0.74

erences

0.72

 commandments

0.70

0.64

 refres

0.63

 wonders

0.62

essee

0.61

behind

0.60

Activations Density 0.200%

DOI numbers

numerical data and references in the context of academic articles or scientific reports

No Comments

No Known Activations