INDEX

Explanations

mentions of specific brands or companies

oai_token-act-pair · gpt-3.5-turbo

references to the term "origin" in various contexts

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

hyde

-0.75

STEM

-0.73

cape

-0.71

flake

-0.70

HCR

-0.68

Case

-0.67

Madison

-0.66

BSD

-0.63

pherd

-0.63

 Immunity

-0.62

POSITIVE LOGITS

inating

1.34

inals

1.34

inally

1.33

ination

1.24

inated

1.24

inate

1.08

inates

1.07

inations

1.00

inal

0.99

inant

0.95

Activations Density 0.029%

mentions of specific brands or companies

references to the term "origin" in various contexts

No Comments

No Known Activations