INDEX

Explanations

verbs indicating a change of understanding or realization

oai_token-act-pair · gpt-3.5-turbo

expressions of realization or understanding

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

nick

-0.69

behind

-0.67

States

-0.67

front

-0.64

 Julius

-0.63

adr

-0.63

Palest

-0.63

Newsletter

-0.63

Britain

-0.62

root

-0.62

POSITIVE LOGITS

 Been

0.85

ãĤ¦ãĤ¹

0.68

°

0.66

 plenty

0.65

ãĥĨ

0.64

 gone

0.64

 Gone

0.63

Tro

0.62

 Plenty

0.60

cedented

0.60

Activations Density 0.102%

verbs indicating a change of understanding or realization

expressions of realization or understanding

No Comments

No Known Activations