INDEX

Explanations

quantitative measurements expressed in numerical forms with decimal points

oai_token-act-pair · gpt-3.5-turbo

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 @ 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

pty

-0.79

ĸļ

-0.75

swick

-0.66

sters

-0.66

ãĤ±

-0.64

Bee

-0.62

icone

-0.61

quit

-0.61

NSA

-0.60

stration

-0.60

POSITIVE LOGITS

Thirty

0.85

ield

0.82

ths

0.75

 gallon

0.73

âĢ³

0.72

inch

0.72

0.71

WD

0.71

Activations Density 0.040%

quantitative measurements expressed in numerical forms with decimal points

numerical data or statistics

No Comments

No Known Activations