INDEX

Explanations

locations or addresses

oai_token-act-pair · gpt-3.5-turbo

references to locations and entities associated with significant events or phenomena

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

AND

-0.82

uador

-0.76

DragonMagazine

-0.69

and

-0.65

ileaks

-0.63

apest

-0.62

"]=>

-0.60

And

-0.59

and

-0.59

-0.58

POSITIVE LOGITS

 lately

0.62

 antics

0.60

 sightings

0.58

 penchant

0.57

 activity

0.56

 frustrations

0.54

Materials

0.54

 possessions

0.54

 stash

0.52

 predicament

0.52

Activations Density 0.712%

locations or addresses

references to locations and entities associated with significant events or phenomena

No Comments

No Known Activations