INDEX

Explanations

things that are located at a higher position relative to other objects

oai_token-act-pair · gpt-3.5-turbo

positions or locations in relation to "above" or "behind."

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

Introduced

-0.77

DN

-0.71

alysis

-0.71

IPP

-0.71

Ì¶

-0.69

agically

-0.68

uten

-0.68

å£«

-0.67

iasis

-0.66

oglu

-0.66

POSITIVE LOGITS

rium

1.03

hang

0.85

tyard

0.80

 midnight

0.79

hung

0.79

 foreground

0.77

 infinity

0.77

 them

0.75

 dusk

0.73

the

0.73

Activations Density 0.192%

things that are located at a higher position relative to other objects

positions or locations in relation to "above" or "behind."

No Known Activations