INDEX

Explanations

phrases related to laws, rights, and societal structures

oai_token-act-pair · gpt-3.5-turbo

concepts related to law and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 winters

-0.68

 finishes

-0.66

TN

-0.66

rosso

-0.66

çĶ°

-0.65

èª

-0.65

 bouts

-0.64

PLA

-0.64

album

-0.62

Lv

-0.62

POSITIVE LOGITS

 conduit

1.08

 tool

1.05

 gateway

0.92

 refuge

0.89

 indispensable

0.87

 battleground

0.86

 guarant

0.85

 infall

0.85

 havens

0.83

 cess

0.83

Activations Density 0.325%

phrases related to laws, rights, and societal structures

concepts related to law and governance

No Comments

No Known Activations