INDEX

Explanations

phrases related to including or involving something

oai_token-act-pair · gpt-3.5-turbo

phrases that describe inclusion or components of something

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ometer

-0.61

ieties

-0.61

 myster

-0.61

iliate

-0.61

apy

-0.60

iasm

-0.60

bell

-0.60

 Sabha

-0.59

uer

-0.59

 proble

-0.59

POSITIVE LOGITS

 prominently

0.68

ãĥ¯

0.68

ãĤ´

0.65

ttes

0.65

ESCO

0.62

ãĥķãĤ©

0.62

ãĤ¯

0.62

ãĥĸ

0.60

++++

0.60

ãĥĨãĤ£

0.59

Activations Density 0.066%

phrases related to including or involving something

phrases that describe inclusion or components of something

No Comments

No Known Activations