INDEX

Explanations

phrases related to the location or person named "Gran"

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Gran" and its variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lovecraft

-0.62

 Laugh

-0.62

BMC

-0.62

åº

-0.61

ORT

-0.60

GMT

-0.60

yers

-0.60

 Gutenberg

-0.60

 Buffett

-0.59

suit

-0.59

POSITIVE LOGITS

vik

0.96

ular

0.95

ules

0.94

igans

0.92

ularity

0.92

vine

0.84

adier

0.84

iosity

0.84

adan

0.82

agraph

0.81

Activations Density 0.017%

phrases related to the location or person named "Gran"

mentions of the word "Gran" and its variations

No Comments

No Known Activations