INDEX

Explanations

information related to legal actions and criminal activities

oai_token-act-pair · gpt-3.5-turbo

phrases related to legal actions or arrests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Newsletter

-1.36

âĹ¼

-0.78

ãĤ¶

-0.74

////////////////////////////////

-0.71

Roaming

-0.70

thumbnails

-0.70

brew

-0.70

Interstitial

-0.68

ãĥ´ãĤ¡

-0.67

©¶æ¥µ

-0.66

POSITIVE LOGITS

 Adelaide

0.76

 watchdog

0.74

 paed

0.74

sex

0.68

 Canberra

0.68

 Perth

0.68

 honoured

0.68

fue

0.67

iership

0.67

 centre

0.67

Activations Density 1.038%

information related to legal actions and criminal activities

phrases related to legal actions or arrests

No Comments

No Known Activations