INDEX

Explanations

mentions of vehicles or related terms

oai_token-act-pair · gpt-3.5-turbo

references to vehicles and their related attributes or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

bread

-0.89

aido

-0.75

artz

-0.71

estamp

-0.70

tale

-0.70

yo

-0.67

ulum

-0.67

 almonds

-0.66

ordial

-0.65

nis

-0.65

POSITIVE LOGITS

 dealership

1.17

 parked

1.12

ousel

1.02

riages

0.98

 drivers

0.94

 transporting

0.90

 fleet

0.88

 occupants

0.88

 manufacturer

0.86

 vehicles

0.85

Activations Density 0.043%

mentions of vehicles or related terms

references to vehicles and their related attributes or contexts

No Comments

No Known Activations