INDEX

Explanations

abbreviations/acronyms followed by a numerical value

oai_token-act-pair · gpt-3.5-turbo

the end of sections or text content markers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orate

-0.85

iard

-0.74

izons

-0.71

urate

-0.70

raising

-0.63

illard

-0.62

acting

-0.61

andel

-0.61

umen

-0.61

jamin

-0.61

POSITIVE LOGITS

eways

0.86

zhen

0.78

atchewan

0.76

plings

0.74

ustain

0.70

cery

0.70

ority

0.69

atoon

0.69

utra

0.69

hett

0.67

Activations Density 0.243%

abbreviations/acronyms followed by a numerical value

the end of sections or text content markers

No Comments

No Known Activations