INDEX

Explanations

specific numbers and technical terms often related to technology or data

oai_token-act-pair · gpt-3.5-turbo

numbers, years, and terms related to specific organizations or formal structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 challeng

-0.56

vou

-0.54

 referen

-0.51

 conduc

-0.51

jri

-0.48

anwhile

-0.48

 furthermore

-0.48

 proport

-0.48

 smelled

-0.48

 acted

-0.47

POSITIVE LOGITS

dom

0.52

abs

0.50

independence

0.49

cigarettes

0.48

 Syndrome

0.47

ds

0.47

brew

0.47

max

0.46

 Genetics

0.46

arenthood

0.46

Activations Density 0.852%

specific numbers and technical terms often related to technology or data

numbers, years, and terms related to specific organizations or formal structures

No Comments

No Known Activations