INDEX

Explanations

terms related to medical services and emergency responses

oai_token-act-pair · gpt-3.5-turbo

phrases related to uncertainty and explanations for events

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 gener

-0.52

)",

-0.51

ysical

-0.51

 ______

-0.50

 Philosophy

-0.50

XY

-0.49

)].

-0.48

[/

-0.48

 Capitalism

-0.48

 Warlock

-0.47

POSITIVE LOGITS

Residents

0.59

 residents

0.55

 onlook

0.54

 sightings

0.54

 mosqu

0.53

 crews

0.53

 belongings

0.52

 Tsarnaev

0.52

 Ramadan

0.52

çĶ°

0.51

Activations Density 2.358%

terms related to medical services and emergency responses

phrases related to uncertainty and explanations for events

No Comments

No Known Activations