INDEX

Explanations

organizations or entities related to various topics

oai_token-act-pair · gpt-3.5-turbo

words related to state or status changes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

é¾įå

-0.78

ISO

-0.73

IB

-0.64

BILITIES

-0.62

å¥³

-0.62

åī

-0.60

Admin

-0.58

$$

-0.58

ACTED

-0.58

IPA

-0.57

POSITIVE LOGITS

hed

0.98

uled

0.94

apeake

0.84

uling

0.83

ding

0.82

rish

0.79

worth

0.79

ules

0.78

tons

0.78

rogens

0.75

Activations Density 0.005%

organizations or entities related to various topics

words related to state or status changes

No Comments

No Known Activations