INDEX

Explanations

questions

oai_token-act-pair · gpt-3.5-turbo

questions relating to personal experiences and opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cipled

-0.73

lap

-0.71

 migr

-0.67

 fanc

-0.64

 swamp

-0.64

anyahu

-0.62

 embro

-0.61

fut

-0.60

ufact

-0.60

 lifes

-0.60

POSITIVE LOGITS

 Answer

1.06

 Obviously

1.05

 Would

1.04

 Explain

1.01

Answer

0.99

 Seems

0.98

.?

0.97

 Certainly

0.96

 Were

0.93

 Probably

0.92

Activations Density 0.080%

questions

questions relating to personal experiences and opinions

No Comments

No Known Activations