INDEX

Explanations

phrases related to similarities or comparisons between different situations or entities

oai_token-act-pair · gpt-3.5-turbo

phrases indicating causation or connections between ideas

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

worthy

-0.58

âĢĲ

-0.56

roy

-0.56

erity

-0.56

oper

-0.55

hess

-0.54

quality

-0.53

 underrated

-0.53

 Raphael

-0.52

orial

-0.52

POSITIVE LOGITS

 redes

0.70

 plague

0.67

[|

0.65

 applies

0.65

uman

0.63

 governs

0.63

osponsors

0.62

brates

0.62

ricanes

0.61

romy

0.60

Activations Density 0.132%

phrases related to similarities or comparisons between different situations or entities

phrases indicating causation or connections between ideas

No Comments

No Known Activations