INDEX

Explanations

specific references to highways or roads including their numbers or locations

oai_token-act-pair · gpt-3.5-turbo

references to infrastructure, particularly roads and highways

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

intosh

-0.74

weet

-0.72

oyal

-0.70

iaries

-0.67

ictive

-0.66

irlfriend

-0.65

Analy

-0.64

vier

-0.64

untu

-0.63

 cellul

-0.62

POSITIVE LOGITS

 highways

1.01

 tunnels

0.97

 corridor

0.95

 corridors

0.94

 intersections

0.89

 bridges

0.86

 Interstate

0.84

 highway

0.83

 junction

0.83

interstitial

0.81

Activations Density 0.587%

specific references to highways or roads including their numbers or locations

references to infrastructure, particularly roads and highways

No Comments

No Known Activations