INDEX

Explanations

references to whales

oai_token-act-pair · gpt-3.5-turbo

references to whales and their related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãĥ´ãĤ¡

-0.83

Rap

-0.79

uers

-0.77

Interstitial

-0.73

 Spiegel

-0.70

Primary

-0.69

ados

-0.69

rival

-0.68

pse

-0.67

DIR

-0.67

POSITIVE LOGITS

 whales

1.50

 whale

1.43

 Whale

1.31

odon

1.10

 sharks

0.97

 dolphins

0.94

 shark

0.89

 hump

0.85

ertodd

0.83

 dolphin

0.78

Activations Density 0.009%

references to whales

references to whales and their related concepts

No Comments

No Known Activations