INDEX

Explanations

proper nouns with 'yr' followed by a number

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ou

-0.84

 Papua

-0.71

leeve

-0.70

ELS

-0.66

 seams

-0.66

 Sahara

-0.66

oise

-0.65

 Chao

-0.64

 Pixie

-0.63

 Samoa

-0.63

POSITIVE LOGITS

rha

1.26

rr

0.90

rh

0.86

andom

0.85

azines

0.82

haps

0.81

mph

0.80

umbn

0.79

hon

0.77

umph

0.76

Activations Density 0.021%

proper nouns with 'yr' followed by a number

No Comments

No Known Activations