INDEX

Explanations

punctuation marks representing certainty or agreement

oai_token-act-pair · gpt-3.5-turbo

statements that affirm or assert facts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 wagon

-0.76

dun

-0.73

 delinquent

-0.68

mud

-0.67

 unseen

-0.65

 unob

-0.64

oing

-0.64

 tranquil

-0.64

 sling

-0.63

ween

-0.63

POSITIVE LOGITS

 Especially

1.08

But

1.07

 Because

1.07

 Unless

1.06

 Whereas

1.01

 Absolutely

0.99

 Certainly

0.98

 However

0.98

 Though

0.96

 Whenever

0.95

Activations Density 0.320%

punctuation marks representing certainty or agreement

statements that affirm or assert facts

No Comments

No Known Activations