INDEX

Explanations

numbers that are related to quantities or measurements

oai_token-act-pair · gpt-3.5-turbo

occurrences of the number "2" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

assetsadobe

-0.63

Tob

-0.58

↵Âł

-0.58

 swearing

-0.58

 Coffin

-0.57

 Lara

-0.57

Sev

-0.56

 Trent

-0.55

 Sacrament

-0.55

ogyn

-0.55

POSITIVE LOGITS

Â½

1.33

1.18

1.10

1.05

1.02

1.01

1.00

 Â½

1.00

Activations Density 0.170%

numbers that are related to quantities or measurements

occurrences of the number "2" in various contexts

No Comments

No Known Activations