INDEX

Explanations

phrases related to the concept of openness or being open

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

ãĤ¨ãĥ«

-0.91

ificent

-0.77

ãĥĥãĥī

-0.75

ãĥĥ

-0.75

=-=-=-=-

-0.74

ippery

-0.74

izarre

-0.74

usky

-0.72

BUS

-0.71

 Frie

-0.70

POSITIVE LOGITS

 syndrome

1.09

 fallacy

0.89

 solutions

0.82

 scenarios

0.79

(>

0.79

nered

0.78

edly

0.77

 theory

0.76

 agreements

0.74

 advocates

0.73

Activations Density 0.373%

phrases related to the concept of openness or being open

No Comments

No Known Activations