INDEX

Explanations

phrases related to governmental actions and policies

oai_token-act-pair · gpt-3.5-turbo

concepts related to choices and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

-0.80

ï¸ı

-0.80

depth

-0.75

":["

-0.69

 frequ

-0.68

particularly

-0.68

often

-0.68

 reputable

-0.67

 Often

-0.67

estones

-0.67

POSITIVE LOGITS

 Frankenstein

1.08

 capit

0.85

 reinvent

0.82

 Trojan

0.81

 equivalent

0.81

 shorthand

0.80

 undo

0.79

 legalized

0.78

 rewriting

0.78

 inverse

0.77

Activations Density 0.406%

phrases related to governmental actions and policies

concepts related to choices and their implications

No Comments

No Known Activations