INDEX

Explanations

comparisons or evaluations indicating a higher or lower degree or quality of something

oai_token-act-pair · gpt-3.5-turbo

phrases that compare or quantify something as being "nothing more than" or "nothing short of" a certain state or quality

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

ahime

-0.84

sten

-0.69

[|

-0.69

 Pengu

-0.68

ppel

-0.65

 Dickinson

-0.65

ascade

-0.64

osen

-0.63

oak

-0.63

 Advertisement

-0.61

POSITIVE LOGITS

 except

0.96

 whatsoever

0.84

 resembling

0.84

pires

0.82

except

0.82

 happening

0.80

 besides

0.76

 transpired

0.73

 happens

0.70

Except

0.68

Activations Density 0.134%

comparisons or evaluations indicating a higher or lower degree or quality of something

phrases that compare or quantify something as being "nothing more than" or "nothing short of" a certain state or quality

No Comments

No Known Activations