INDEX

Explanations

mentions of a sports team named "Sporting."

oai_token-act-pair · gpt-3.5-turbo

references to the term "Sporting," specifically relating to sports teams or venues

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

inventoryQuantity

-0.84

onym

-0.81

Reviewer

-0.77

iod

-0.76

upon

-0.71

river

-0.67

 disg

-0.67

onse

-0.67

ylum

-0.67

oxy

-0.65

POSITIVE LOGITS

 Sporting

1.05

folios

0.94

KC

0.94

 Kansas

0.93

ocity

0.90

 Goods

0.85

 Lisbon

0.83

KC

0.81

stal

0.81

idad

0.75

Activations Density 0.026%

mentions of a sports team named "Sporting."

references to the term "Sporting," specifically relating to sports teams or venues

No Comments

No Known Activations