INDEX

Explanations

locations in different cities

oai_token-act-pair · gpt-3.5-turbo

prominent locations or cities mentioned in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Reviewer

-0.73

Ps

-0.67

 Flavoring

-0.65

merce

-0.65

Ü

-0.64

omorph

-0.64

Marginal

-0.63

phabet

-0.62

ographers

-0.62

 recip

-0.62

POSITIVE LOGITS

Bay

0.97

 Meadows

0.95

 Harbor

0.91

 harbor

0.82

 suburb

0.82

 Heights

0.82

 Harbour

0.81

hesda

0.81

 suburbs

0.79

 Manhattan

0.75

Activations Density 0.225%

locations in different cities

prominent locations or cities mentioned in the document

No Comments

No Known Activations