INDEX

Explanations

numbers with units of measurement

oai_token-act-pair · gpt-3.5-turbo

various quantitative measures and specifications related to limits, distances, and economic factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

nu

-0.66

']

-0.64

Tea

-0.63

 Gods

-0.62

tnc

-0.61

 gluc

-0.61

íķ

-0.60

farious

-0.60

theless

-0.59

âĹ¼

-0.59

POSITIVE LOGITS

 apiece

0.95

(~

0.68

 sandwic

0.68

 weighs

0.67

 compared

0.67

 diameter

0.66

athon

0.66

 commute

0.66

itent

0.65

 encomp

0.65

Activations Density 0.296%

numbers with units of measurement

various quantitative measures and specifications related to limits, distances, and economic factors

No Comments

No Known Activations