INDEX

Explanations

words related to licenses and permits

oai_token-act-pair · gpt-3.5-turbo

words related to licenses and licensing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Samoa

-0.88

 Annotations

-0.79

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.72

ORGE

-0.69

 Hole

-0.69

eering

-0.69

 Andromeda

-0.68

 Airl

-0.68

 Lans

-0.68

ãĥ¯ãĥ³

-0.67

POSITIVE LOGITS

ensing

1.27

enses

1.10

anc

1.05

lic

0.99

entious

0.96

enced

0.89

ence

0.89

ornia

0.87

inda

0.87

ensed

0.87

Activations Density 0.013%

words related to licenses and permits

words related to licenses and licensing

No Comments

No Known Activations