INDEX

Explanations

political and legal terms or phrases

oai_token-act-pair · gpt-3.5-turbo

punctuation marks and symbols used in textual context

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

orer

-0.73

oir

-0.71

ARCH

-0.68

OND

-0.64

isers

-0.61

NK

-0.61

Gw

-0.60

alty

-0.57

SPA

-0.57

ocial

-0.57

POSITIVE LOGITS

FontSize

0.67

0.64

 respectively

0.64

bet

0.63

 Kard

0.62

otos

0.61

 destro

0.61

 disg

0.60

etheless

0.60

 signifies

0.60

Activations Density 0.742%

political and legal terms or phrases

punctuation marks and symbols used in textual context

No Comments

No Known Activations