INDEX

Explanations

phrases related to observation or understanding

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing observation or perception

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

nor

-0.82

due

-0.80

FIR

-0.70

lique

-0.70

utenberg

-0.69

iosyn

-0.68

adh

-0.68

 confir

-0.68

uala

-0.68

aith

-0.68

POSITIVE LOGITS

 yourselves

1.00

 yourself

0.97

me

0.70

 billboards

0.70

 guys

0.68

why

0.67

 everywhere

0.67

dust

0.66

 here

0.64

 what

0.63

Activations Density 0.081%

phrases related to observation or understanding

phrases emphasizing observation or perception

No Known Activations