INDEX

Explanations

questions related to decision-making and consequences

oai_token-act-pair · gpt-3.5-turbo

interrogative phrases that pose questions or seek clarification

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

IM

-0.69

weed

-0.66

imb

-0.63

che

-0.62

Cele

-0.62

morph

-0.61

trop

-0.61

BOX

-0.61

wide

-0.60

pin

-0.60

POSITIVE LOGITS

 subsequ

0.74

)?

0.74

 glim

0.74

 millenn

0.70

'?

0.69

 losers

0.67

eday

0.66

?'

0.65

srf

0.64

 surpr

0.64

Activations Density 0.093%

questions related to decision-making and consequences

interrogative phrases that pose questions or seek clarification

No Comments

No Known Activations