INDEX

Explanations

postal abbreviations or acronyms

oai_token-act-pair · gpt-3.5-turbo

acronyms or abbreviations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ãĥ¼ãĥĨãĤ£

-0.92

geist

-0.76

unia

-0.75

flies

-0.74

ãĥĥãĥĪ

-0.73

wall

-0.72

ication

-0.70

orious

-0.68

uran

-0.68

ãĥĥãĥī

-0.66

POSITIVE LOGITS

JO

1.16

BIL

1.15

BI

1.14

VE

1.13

OTS

1.13

INT

1.13

BO

1.09

FILE

1.06

VER

1.06

ONEY

1.05

Activations Density 0.029%

postal abbreviations or acronyms

acronyms or abbreviations

No Comments

No Known Activations