INDEX

Explanations

references to the name "Gurmeet Ram Rahim Singh Ji Insan."

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals, particularly related to names or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Creed

-0.71

perature

-0.67

 Tune

-0.65

 Phant

-0.64

 NATO

-0.64

OTAL

-0.62

olitan

-0.59

ACTED

-0.59

 Roche

-0.59

çīĪ

-0.59

POSITIVE LOGITS

iosity

1.21

Gur

1.04

iants

0.96

imental

0.91

illas

0.90

rily

0.90

mud

0.89

nar

0.87

rets

0.87

ithub

0.86

Activations Density 0.011%

references to the name "Gurmeet Ram Rahim Singh Ji Insan."

references to specific individuals, particularly related to names or titles

No Comments

No Known Activations