INDEX

Explanations

distances or measurements typically represented in miles

oai_token-act-pair · gpt-3.5-turbo

references to distances or measurements in miles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

eer

-0.84

alien

-0.72

eers

-0.67

gotten

-0.66

ãĥ¤

-0.64

Suc

-0.64

istry

-0.63

icer

-0.62

icious

-0.61

olith

-0.61

POSITIVE LOGITS

 traveled

0.91

 kilometers

0.91

 kilometres

0.87

km

0.85

bike

0.85

 radius

0.83

 travelled

0.82

km

0.81

 miles

0.79

 circumference

0.77

Activations Density 0.039%

distances or measurements typically represented in miles

references to distances or measurements in miles

No Comments

No Known Activations