INDEX

Explanations

phrases related to manufacturing

oai_token-act-pair · gpt-3.5-turbo

terms related to manufacturing processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

pan

-0.85

hov

-0.72

tein

-0.69

early

-0.68

hus

-0.68

immers

-0.66

sen

-0.63

rella

-0.62

alon

-0.62

ander

-0.61

POSITIVE LOGITS

 manufactured

1.09

 manufacture

1.06

 manufactures

1.04

 manufacturing

0.97

 Manufact

0.96

 fabrication

0.96

 manufact

0.92

 Manufacturing

0.81

urers

0.80

entanyl

0.79

Activations Density 0.005%

phrases related to manufacturing

terms related to manufacturing processes

No Comments

No Known Activations