INDEX

Explanations

the word "many" occurring multiple times in a document

oai_token-act-pair · gpt-3.5-turbo

repeated patterns or phrases indicating quantity or frequency

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

acus

-0.81

atum

-0.75

iasis

-0.71

OPE

-0.71

istan

-0.71

adish

-0.71

etry

-0.71

amation

-0.70

ataka

-0.68

IPP

-0.68

POSITIVE LOGITS

 times

1.01

 facets

0.99

 aspects

0.93

body

0.90

 kinds

0.89

 unanswered

0.85

 iterations

0.83

 thousands

0.82

 different

0.82

 ways

0.82

Activations Density 0.070%

the word "many" occurring multiple times in a document

repeated patterns or phrases indicating quantity or frequency

No Comments

No Known Activations