INDEX

Explanations

formal punctuation marks

oai_token-act-pair · gpt-3.5-turbo

references to specific political or national security contexts

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

 richer

-0.75

wagen

-0.75

 wealthier

-0.70

ãĤ·ãĥ£

-0.69

 cradle

-0.68

ãĥĦ

-0.67

 explan

-0.65

ãĤ´ãĥ³

-0.63

ãĥ´

-0.62

 therap

-0.61

POSITIVE LOGITS

-.

0.94

ISO

0.93

."

0.89

Ħ¢

0.79

..

0.77

Mol

0.76

mil

0.75

RFC

0.74

wav

0.72

Activations Density 0.023%

formal punctuation marks

references to specific political or national security contexts

No Comments

No Known Activations