INDEX

Explanations

phrases or instances of the word "word" being used in text

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "word" and related terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jri

-0.78

âĹ¼

-0.76

vic

-0.68

DERR

-0.67

arling

-0.63

ockets

-0.62

 millenn

-0.62

haar

-0.60

umerable

-0.60

outube

-0.59

POSITIVE LOGITS

ultimate

0.98

 itself

0.93

0.80

tymology

0.77

icide

0.76

 interchange

0.69

scape

0.67

\"

0.66

''

0.66

Activations Density 0.075%

phrases or instances of the word "word" being used in text

occurrences of the word "word" and related terms

No Comments

No Known Activations