INDEX

Explanations

references to or mentions of items or objects called "plates"

oai_token-act-pair · gpt-3.5-turbo

references to plates, particularly in the context of food or license plates

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

Negative Logits

vernment

-1.03

Plug

-0.79

rians

-0.76

apest

-0.75

ndra

-0.72

naissance

-0.68

ITNESS

-0.68

Kut

-0.68

ruary

-0.68

emouth

-0.66

POSITIVE LOGITS

 plates

1.08

 plate

1.04

plate

0.99

ographer

0.91

meal

0.86

aus

0.85

 armour

0.80

washer

0.80

 Plate

0.76

cloth

0.76

Activations Density 0.018%

references to or mentions of items or objects called "plates"

references to plates, particularly in the context of food or license plates

No Known Activations