INDEX

Explanations

names of people

oai_token-act-pair · gpt-3.5-turbo

names and associated titles or roles of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 stale

-0.50

',"

-0.50

 reliant

-0.48

 deterrent

-0.46

?'"

-0.46

,'"

-0.46

 vulnerability

-0.45

?".

-0.45

,'

-0.44

 corros

-0.44

POSITIVE LOGITS

çĶ°

0.60

ospons

0.60

itled

0.54

ãĥĬ

0.54

çļ

0.52

itone

0.52

anky

0.51

anan

0.51

å·

0.48

aug

0.48

Activations Density 2.528%

names of people

names and associated titles or roles of individuals

No Comments

No Known Activations