INDEX

Explanations

the conjunction "which is" patterns

oai_token-act-pair · gpt-3.5-turbo

statements indicating definitions or explanations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otte

-0.86

actory

-0.76

rongh

-0.73

ievers

-0.72

nikov

-0.70

arella

-0.67

icators

-0.67

oided

-0.66

Numbers

-0.65

igraph

-0.63

POSITIVE LOGITS

why

1.49

 understandable

1.13

 admittedly

1.11

 ironic

1.05

 presumably

1.05

 basically

1.02

why

1.00

 supposed

0.94

WHY

0.93

 exactly

0.93

Activations Density 0.118%

the conjunction "which is" patterns

statements indicating definitions or explanations

No Comments

No Known Activations