INDEX

Explanations

terms related to physical locations like warehouses

oai_token-act-pair · gpt-3.5-turbo

references to warehouses

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

utan

-0.69

nir

-0.69

azeera

-0.67

pend

-0.64

bernatorial

-0.63

uated

-0.63

reme

-0.62

cific

-0.62

omsky

-0.62

ulus

-0.61

POSITIVE LOGITS

 warehouse

1.05

 warehouses

1.04

yard

1.00

 shelves

0.87

 Warehouse

0.87

 guiActiveUnfocused

0.87

 Depot

0.84

housing

0.83

yards

0.80

eers

0.79

Activations Density 0.010%

terms related to physical locations like warehouses

references to warehouses

No Comments

No Known Activations