INDEX

Explanations

numerical values related to a ranking or order

oai_token-act-pair · gpt-3.5-turbo

numeric values and data points

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

TextColor

-0.80

netflix

-0.77

rely

-0.76

inic

-0.67

stood

-0.66

ques

-0.65

rette

-0.63

 propriet

-0.62

unct

-0.61

deen

-0.61

POSITIVE LOGITS

acity

1.00

0.86

tons

0.84

^{

0.83

0.81

th

0.81

ths

0.80

0.79

%"

0.79

Activations Density 0.072%

numerical values related to a ranking or order

numeric values and data points

No Comments

No Known Activations