INDEX

Explanations

time-related phrases and mentions of specific days or times

oai_token-act-pair · gpt-3.5-turbo

references to time durations and significant time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

senal

-0.55

onto

-0.53

luster

-0.52

anamo

-0.50

emale

-0.49

 outwe

-0.47

existent

-0.46

 vulner

-0.46

Els

-0.46

 abound

-0.45

POSITIVE LOGITS

][

0.55

imester

0.47

catentry

0.47

!--

0.46

 Publication

0.46

 embodiments

0.45

pite

0.44

 however

0.43

 Background

0.42

ITNESS

0.42

Activations Density 0.666%

time-related phrases and mentions of specific days or times

references to time durations and significant time periods

No Comments

No Known Activations