INDEX

Explanations

technical terms with the prefix "co-" followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

terms related to cooperation or collaborative efforts

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

HCR

-0.78

ICAN

-0.75

IONS

-0.71

 Rite

-0.71

 GOODMAN

-0.69

 Skydragon

-0.67

 Fourth

-0.66

 Ninth

-0.65

 Judgment

-0.65

shire

-0.64

POSITIVE LOGITS

olly

1.12

venants

1.10

herence

1.00

hab

0.93

eding

0.92

ingen

0.91

ops

0.90

herent

0.89

ven

0.88

erc

0.88

Activations Density 0.025%

technical terms with the prefix "co-" followed by a numerical value

terms related to cooperation or collaborative efforts

No Comments

No Known Activations