INDEX

Explanations

specific brand names, especially related to food products

oai_token-act-pair · gpt-3.5-turbo

references to environmental issues related to specific brands

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

istically

-0.84

fare

-0.75

ãģĦ

-0.75

WAYS

-0.73

++++++++++++++++

-0.71

~~~~~~~~~~~~~~~~

-0.69

JFK

-0.67

à¤¾

-0.67

 ACTIONS

-0.66

 setbacks

-0.66

POSITIVE LOGITS

lÃ©

1.27

orius

1.08

 Nest

1.05

ea

1.01

eus

0.94

eas

0.87

zen

0.87

hes

0.85

ensibly

0.85

ovo

0.84

Activations Density 0.011%

specific brand names, especially related to food products

references to environmental issues related to specific brands

No Comments

No Known Activations