INDEX

Explanations

keywords related to instructions or commands

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "just" in various forms

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

 Palestin

-0.75

egal

-0.71

 undermin

-0.68

 Pett

-0.68

 Archdemon

-0.63

 seiz

-0.62

 conflic

-0.62

 conscientious

-0.61

 plaintiff

-0.61

sac

-0.60

POSITIVE LOGITS

ifications

0.96

ifiable

0.88

 plain

0.87

 kidding

0.86

ices

0.81

ijn

0.81

ified

0.79

FY

0.78

ify

0.77

IFIC

0.77

Activations Density 0.077%

keywords related to instructions or commands

occurrences of the word "just" in various forms

No Comments

No Known Activations