INDEX

Explanations

acronyms related to organizations

oai_token-act-pair · gpt-3.5-turbo

abbreviations or acronyms related to organizations and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

perse

-0.72

enegger

-0.71

heimer

-0.68

initialized

-0.66

 tion

-0.66

flies

-0.65

sov

-0.64

accompanied

-0.64

fitting

-0.63

wagen

-0.63

POSITIVE LOGITS

AN

1.05

OE

1.05

Ps

1.02

OF

1.02

Bs

1.01

BC

0.97

UF

0.95

RM

0.95

IENT

0.95

PLIC

0.94

Activations Density 0.116%

acronyms related to organizations

abbreviations or acronyms related to organizations and processes

No Comments

No Known Activations