INDEX

Explanations

expressions related to ways or methods

oai_token-act-pair · gpt-3.5-turbo

references to ways or methods of achieving something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

halla

-0.70

ONSORED

-0.70

ADRA

-0.68

opsis

-0.67

wine

-0.66

oos

-0.66

thumbnails

-0.65

 Thumbnails

-0.65

©¶æ¥µ

-0.63

aples

-0.63

POSITIVE LOGITS

terday

0.93

Ðº

0.73

 whereby

0.69

fare

0.68

forward

0.66

ivism

0.64

hift

0.63

Ð»

0.63

pace

0.61

ãĥ¼ãĥĨãĤ£

0.61

Activations Density 0.033%

expressions related to ways or methods

references to ways or methods of achieving something

No Comments

No Known Activations