INDEX

Explanations

phrases related to comparisons between different entities or concepts

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

escription

-0.97

chnology

-0.71

oval

-0.64

 Ended

-0.64

isure

-0.63

 behalf

-0.63

prise

-0.63

mire

-0.62

lift

-0.62

encia

-0.62

POSITIVE LOGITS

 except

1.04

 albeit

0.96

 although

0.86

 insofar

0.85

but

0.84

though

0.80

nor

0.80

but

0.78

although

0.77

 though

0.74

Activations Density 0.300%

phrases related to comparisons between different entities or concepts

No Comments

No Known Activations