INDEX

Explanations

mentions of specific locations

oai_token-act-pair · gpt-3.5-turbo

repeated occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

omever

-0.74

pointers

-0.73

natureconservancy

-0.71

bnb

-0.70

aurus

-0.70

sers

-0.69

uture

-0.68

vantage

-0.67

arians

-0.67

strap

-0.67

POSITIVE LOGITS

 wake

1.26

 midst

1.22

 aftermath

1.16

 meantime

1.10

 guise

1.04

wee

1.02

 Netherlands

0.97

 waning

0.91

 Philippines

0.91

 Bahamas

0.90

Activations Density 0.229%

mentions of specific locations

repeated occurrences of the word "the."

No Comments

No Known Activations