INDEX

Explanations

expressions describing large quantities or amounts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "entire" used in various contexts

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

ju

-0.76

ker

-0.67

bid

-0.67

akers

-0.66

 advoc

-0.65

aline

-0.63

ific

-0.62

KER

-0.61

acon

-0.61

 Chaser

-0.60

POSITIVE LOGITS

hearted

0.85

heartedly

0.84

 length

0.79

ength

0.76

 arsenal

0.74

gam

0.74

 contents

0.71

 spectrum

0.71

oven

0.69

 suite

0.68

Activations Density 0.020%

expressions describing large quantities or amounts

instances of the word "entire" used in various contexts

No Comments

No Known Activations