INDEX

Explanations

words related to changes or transformations occurring over time

oai_token-act-pair · gpt-3.5-turbo

words that indicate processes of growth, decline, or change

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ħĭ

-0.71

pperc

-0.67

 stub

-0.67

 simplified

-0.66

isi

-0.65

 pulp

-0.64

chens

-0.63

 canned

-0.63

anooga

-0.63

 unloaded

-0.61

POSITIVE LOGITS

hower

0.88

uate

0.88

uated

0.78

uating

0.74

 Waves

0.73

cycles

0.72

 thro

0.68

uates

0.68

 phenomena

0.68

interstitial

0.67

Activations Density 0.154%

words related to changes or transformations occurring over time

words that indicate processes of growth, decline, or change

No Comments

No Known Activations