INDEX

Explanations

names of people and places

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or symbol used consistently throughout the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 mathemat

-0.77

 disadvant

-0.76

 mosqu

-0.74

 satell

-0.71

 carbohyd

-0.70

 regul

-0.69

omination

-0.69

 succession

-0.67

 township

-0.65

 Tulsa

-0.63

POSITIVE LOGITS

ï¸ı

1.05

hood

0.99

eal

0.86

ship

0.80

VICE

0.79

ï¸

0.78

backer

0.78

own

0.78

ery

0.77

tracks

0.77

Activations Density 0.268%

names of people and places

instances of a specific character or symbol used consistently throughout the text

No Comments

No Known Activations