INDEX

Explanations

phrases related to making a positive impact or change

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize making a difference or impact

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

©¶æ

-0.77

 faults

-0.69

 crab

-0.66

oked

-0.66

 contracted

-0.64

 fault

-0.64

Ü

-0.64

 quotation

-0.62

ç«

-0.62

stra

-0.60

POSITIVE LOGITS

hole

0.76

elight

0.74

inois

0.64

inel

0.64

profits

0.63

Offline

0.63

 (Â£

0.62

Shape

0.62

holes

0.61

eful

0.61

Activations Density 0.033%

phrases related to making a positive impact or change

phrases that emphasize making a difference or impact

No Comments

No Known Activations