INDEX

Explanations

phrases ending in "-ube"

oai_token-act-pair · gpt-3.5-turbo

variations of the word "tube."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĥ£

-0.94

ingham

-0.65

alez

-0.63

rieve

-0.63

 Attribution

-0.63

sheet

-0.63

 ozone

-0.62

IVES

-0.62

matic

-0.61

IVE

-0.59

POSITIVE LOGITS

ube

1.04

cles

0.81

hub

0.79

uf

0.78

ÄŁ

0.75

lda

0.75

 Goldberg

0.71

Pes

0.71

ffer

0.70

Tip

0.68

Activations Density 0.010%

phrases ending in "-ube"

variations of the word "tube."

No Comments

No Known Activations