INDEX

Explanations

phrases that indicate a preference for one option over another

oai_token-act-pair · gpt-3.5-turbo

comparisons emphasizing preference or choice over alternatives

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

mberg

-0.69

ppa

-0.63

hemy

-0.63

endum

-0.61

otti

-0.61

rats

-0.60

inka

-0.59

ORY

-0.58

tsky

-0.58

 Kard

-0.57

POSITIVE LOGITS

 than

1.56

than

1.26

 Than

0.97

 then

0.81

Th

0.67

Else

0.67

TH

0.64

 compared

0.63

 resembling

0.63

 suited

0.63

Activations Density 0.016%

phrases that indicate a preference for one option over another

comparisons emphasizing preference or choice over alternatives

No Comments

No Known Activations