INDEX

Explanations

text related to the acronym "IM"

oai_token-act-pair · gpt-3.5-turbo

references to management or managerial roles

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

yards

-0.82

velt

-0.80

Downloadha

-0.67

 Vale

-0.67

 Kirin

-0.66

hma

-0.64

 Leth

-0.61

ieve

-0.61

ingen

-0.61

heid

-0.60

POSITIVE LOGITS

MY

1.17

PLE

1.14

HO

1.05

ITED

1.05

BER

1.05

MER

1.03

MED

1.02

bledon

1.02

BO

1.00

PLIC

0.98

Activations Density 0.012%

text related to the acronym "IM"

references to management or managerial roles

No Comments

No Known Activations