INDEX

Explanations

adjectives describing quality or skill, particularly those with positive connotations

oai_token-act-pair · gpt-3.5-turbo

expressions of high quality or excellence

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

ople

-0.74

eters

-0.71

mber

-0.68

ocry

-0.67

othy

-0.67

pper

-0.67

aters

-0.64

 Lyons

-0.63

hip

-0.63

 Mellon

-0.62

POSITIVE LOGITS

enough

1.00

sword

0.83

 sounding

0.82

 luck

0.78

 fits

0.75

bye

0.74

nat

0.72

 karma

0.72

 smelling

0.72

nosis

0.71

Activations Density 0.060%

adjectives describing quality or skill, particularly those with positive connotations

expressions of high quality or excellence

No Comments

No Known Activations