INDEX

Explanations

locations or places mentioned in a text

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "on" in various contexts

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

acters

-0.84

DragonMagazine

-0.68

otle

-0.67

Apps

-0.63

MpServer

-0.62

TPP

-0.62

rums

-0.62

NSA

-0.61

boxing

-0.61

ovych

-0.61

POSITIVE LOGITS

 Route

1.09

 Highway

1.03

 campus

1.02

 Saturdays

1.01

 Boulevard

0.99

shore

0.98

yx

0.98

etime

0.98

 Sundays

0.97

 Canal

0.95

Activations Density 0.141%

locations or places mentioned in a text

occurrences of the phrase "on" in various contexts

No Comments

No Known Activations