INDEX

Explanations

decimal numbers in a specific format

oai_token-act-pair · gpt-3.5-turbo

periods or decimal values that signify measurements or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bos

-0.73

 shroud

-0.71

 traveler

-0.68

 beauty

-0.68

 lady

-0.68

 bunny

-0.67

 testament

-0.64

 scourge

-0.64

 performer

-0.64

 worsh

-0.64

POSITIVE LOGITS

Downloadha

1.08

jpg

1.06

1.04

1.01

1.00

0.99

0.98

0.97

Activations Density 0.124%

decimal numbers in a specific format

periods or decimal values that signify measurements or statistics

No Comments

No Known Activations