INDEX

Explanations

words related to legal and law enforcement activities

oai_token-act-pair · gpt-3.5-turbo

instances of significant events or incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 liner

-0.85

 additionally

-0.83

 tasting

-0.82

 retard

-0.81

 furthermore

-0.81

 Tsukuyomi

-0.81

 crumble

-0.80

 moreover

-0.80

 eleph

-0.80

 correlated

-0.80

POSITIVE LOGITS

Former

1.67

Two

1.64

Thousands

1.63

Three

1.62

Published

1.61

Hundreds

1.61

An

1.59

Updated

1.59

Four

1.57

Scientists

1.56

Activations Density 0.150%

words related to legal and law enforcement activities

instances of significant events or incidents

No Comments

No Known Activations