INDEX

Explanations

names, particularly the name "Laura"

oai_token-act-pair · gpt-3.5-turbo

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

cffff

-0.79

rated

-0.72

nings

-0.68

*/(

-0.66

fleet

-0.66

rue

-0.65

hire

-0.65

mental

-0.64

MENTS

-0.63

cffffcc

-0.63

POSITIVE LOGITS

 Jane

1.08

 Palmer

1.04

 Bates

0.90

 Bloom

0.89

Ing

0.87

Jane

0.84

anne

0.82

Vo

0.81

 Bush

0.80

 Anne

0.79

Activations Density 0.031%

names, particularly the name "Laura"

No Comments

No Known Activations