INDEX

Explanations

keywords related to the political figure "Haw" along with associated terms and actions

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

 Winchester

-0.73

ALLY

-0.70

 tant

-0.69

Memory

-0.63

 Mankind

-0.63

 abundantly

-0.60

onial

-0.59

 congr

-0.59

 mort

-0.59

$$$$

-0.58

POSITIVE LOGITS

keye

1.43

aii

1.37

keyes

1.11

kish

1.04

atche

0.99

orth

0.97

king

0.94

ker

0.93

kinson

0.92

sers

0.92

Activations Density 0.097%

keywords related to the political figure "Haw" along with associated terms and actions

No Comments

No Known Activations