INDEX

Explanations

words related to condiments and food items

oai_token-act-pair · gpt-3.5-turbo

words related to place names and geographical locations

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

xual

-0.73

 guiActiveUn

-0.69

DAQ

-0.68

 attribution

-0.67

ysis

-0.65

 inhibitors

-0.64

pta

-0.64

 eligibility

-0.64

 editorial

-0.61

 omission

-0.60

POSITIVE LOGITS

ocks

0.77

lyn

0.75

ath

0.75

leans

0.75

ford

0.75

omed

0.73

lehem

0.73

haven

0.72

sey

0.72

rill

0.70

Activations Density 0.190%

words related to condiments and food items

words related to place names and geographical locations

No Comments

No Known Activations