INDEX

Explanations

financial values expressed in terms of millions of dollars

oai_token-act-pair · gpt-3.5-turbo

sentences that assert the existence or presence of something

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iard

-0.86

umar

-0.75

ievers

-0.72

stad

-0.69

iffe

-0.66

eor

-0.64

ip

-0.62

luaj

-0.62

aft

-0.62

 rode

-0.61

POSITIVE LOGITS

 unbelievable

0.97

 astounding

0.97

 nothing

0.96

 basically

0.95

 extraordinary

0.93

 priceless

0.92

 amazing

0.91

 unacceptable

0.89

 essentially

0.87

 incredible

0.87

Activations Density 0.179%

financial values expressed in terms of millions of dollars

sentences that assert the existence or presence of something

No Comments

No Known Activations