INDEX

Explanations

phrases related to resting or being in a resting place

oai_token-act-pair · gpt-3.5-turbo

references to resting or the concept of rest

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

å¥³

-0.73

inx

-0.69

Allen

-0.69

FK

-0.67

bis

-0.64

Miller

-0.64

holes

-0.64

unch

-0.63

ju

-0.62

lear

-0.61

POSITIVE LOGITS

 resting

0.98

ructure

0.90

ricting

0.88

raint

0.86

itution

0.85

 rests

0.84

nesota

0.81

oleon

0.80

 rested

0.77

orse

0.73

Activations Density 0.008%

phrases related to resting or being in a resting place

references to resting or the concept of rest

No Comments

No Known Activations