INDEX

Explanations

numbers within texts

oai_token-act-pair · gpt-3.5-turbo

phrases or sentences that indicate questions or inquiries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

wagen

-0.84

creen

-0.74

oulos

-0.71

 Canaver

-0.66

nesday

-0.66

 unchecked

-0.66

 Asheville

-0.66

 guiActiveUnfocused

-0.65

 Mellon

-0.65

 general

-0.64

POSITIVE LOGITS

________________________________________________________________

1.08

~~~~~~~~~~~~~~~~

0.97

É

0.94

------------------------

0.93

Ëľ

0.93

---------------

0.92

********

0.92

****************

0.92

~~~~~~~~

0.91

ãĥĪ

0.91

Activations Density 0.005%

numbers within texts

phrases or sentences that indicate questions or inquiries

No Comments

No Known Activations