INDEX

Explanations

phrases related to household activities or characteristics

oai_token-act-pair · gpt-3.5-turbo

references to households

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ache

-0.66

word

-0.66

ixir

-0.62

JC

-0.62

 Nothing

-0.62

ope

-0.61

rex

-0.61

uin

-0.61

YN

-0.61

ace

-0.61

POSITIVE LOGITS

 households

3.56

 household

2.18

 Household

2.14

 families

1.86

 homes

1.64

 dwellings

1.64

 residences

1.56

 homeowners

1.51

 houses

1.38

 neighborhoods

1.35

Activations Density 0.010%

phrases related to household activities or characteristics

references to households

No Comments

No Known Activations