INDEX

Explanations

terms related to names and titles

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of people and places

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 innocence

-0.72

 welf

-0.70

 temptation

-0.66

 aristocracy

-0.66

 knees

-0.65

 moderation

-0.64

 pasture

-0.64

 linen

-0.64

 camel

-0.64

 millennium

-0.64

POSITIVE LOGITS

INAL

1.06

ICT

0.84

ALLY

0.80

OY

0.72

oti

0.72

ãĥ¼ãĥ³

0.71

oxide

0.70

INO

0.69

xual

0.69

nels

0.69

Activations Density 0.114%

terms related to names and titles

proper nouns, particularly names of people and places

No Comments

No Known Activations