INDEX

Explanations

phrases related to accomplishing a task or achieving success

oai_token-act-pair · gpt-3.5-turbo

expressions of repetitive actions or occurrences

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

currently

-0.80

ibles

-0.80

 Continued

-0.66

ao

-0.64

Americ

-0.62

ongo

-0.61

ior

-0.60

 hereafter

-0.60

yond

-0.60

 Proceed

-0.59

POSITIVE LOGITS

 brilliantly

0.78

Ö¼

0.73

 spree

0.64

 unconsciously

0.63

ULE

0.63

ä»£

0.63

kef

0.62

ĸļ

0.61

kefeller

0.60

umerable

0.60

Activations Density 0.268%

phrases related to accomplishing a task or achieving success

expressions of repetitive actions or occurrences

No Comments

No Known Activations