INDEX

Explanations

phrases related to knowledge or lack thereof

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a lack of knowledge or certainty

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

hement

-0.84

 sidx

-0.80

erate

-0.78

igham

-0.73

odder

-0.72

uably

-0.71

ramid

-0.70

rative

-0.69

vertisement

-0.69

nir

-0.68

POSITIVE LOGITS

 whereabouts

0.78

 firsthand

0.76

 beforehand

0.73

 intimately

0.73

 secret

0.73

CHAT

0.72

 secrets

0.68

æĿ

0.67

ledged

0.67

Orig

0.63

Activations Density 0.254%

phrases related to knowledge or lack thereof

phrases indicating a lack of knowledge or certainty

No Comments

No Known Activations