INDEX

Explanations

date references specifically in the year 2016

oai_token-act-pair · gpt-3.5-turbo

references to the year 2016

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

angs

-0.69

FACE

-0.64

onds

-0.64

imar

-0.64

 snipp

-0.63

imen

-0.62

achu

-0.62

phia

-0.62

iple

-0.61

ape

-0.60

POSITIVE LOGITS

1.10

å¹

0.84

bleacher

0.81

âĢ²

0.70

 Became

0.70

ileaks

0.68

âĢ³

0.67

nd

0.67

 Countdown

0.66

Activations Density 0.038%

date references specifically in the year 2016

references to the year 2016

No Comments

No Known Activations