INDEX

Explanations

statistical or numerical data

oai_token-act-pair · gpt-3.5-turbo

instances of the word "figures," indicating numerical data or statistics

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

ModLoader

-0.99

Interstitial

-0.93

osi

-0.81

POSE

-0.74

sole

-0.68

vid

-0.68

ecast

-0.67

GBT

-0.67

 Governors

-0.66

struction

-0.65

POSITIVE LOGITS

heet

0.92

 figures

0.90

 estimates

0.82

 charts

0.78

 tallied

0.76

peak

0.75

 collected

0.75

 estimate

0.74

oil

0.74

hift

0.73

Activations Density 0.047%

statistical or numerical data

instances of the word "figures," indicating numerical data or statistics

No Comments

No Known Activations