INDEX

Explanations

specific mentions of the term "AP" followed by a number

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation 'AP'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

terday

-0.72

wagen

-0.70

catch

-0.65

glers

-0.63

 aver

-0.62

 stabil

-0.61

gaard

-0.61

 thumbs

-0.60

fry

-0.60

 disarm

-0.59

POSITIVE LOGITS

PLE

1.19

TN

1.16

PLIC

1.15

PLIED

1.14

PROV

1.13

PLA

1.11

PRO

1.10

OE

1.07

PAR

1.06

Cs

1.04

Activations Density 0.017%

specific mentions of the term "AP" followed by a number

occurrences of the abbreviation 'AP'

No Comments

No Known Activations