INDEX

Explanations

mentions of distances, particularly in miles

oai_token-act-pair · gpt-3.5-turbo

references to distances measured in miles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

*/(

-0.80

oras

-0.72

orescent

-0.70

ivia

-0.70

PsyNetMessage

-0.68

apt

-0.67

aina

-0.66

ogyn

-0.65

amate

-0.63

uits

-0.63

POSITIVE LOGITS

 mile

0.88

bike

0.81

strument

0.74

 radius

0.73

 kilomet

0.72

 Kenya

0.70

ghan

0.69

 acre

0.69

 Kenyan

0.67

 kilometers

0.67

Activations Density 0.011%

mentions of distances, particularly in miles

references to distances measured in miles

No Comments

No Known Activations