INDEX

Explanations

numerical values followed by symbols or names related to programming or technology

oai_token-act-pair · gpt-3.5-turbo

specialized technical terms and identifiers related to programming or data management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

KB

-0.83

 Labyrinth

-0.80

 Lump

-0.79

 Opera

-0.76

Zig

-0.74

MB

-0.73

 Gear

-0.73

 Flav

-0.72

POSITIVE LOGITS

re

1.61

RE

1.26

rez

1.21

rem

1.15

reb

1.09

ere

1.07

rey

1.06

andre

1.05

rep

1.05

arre

1.04

Activations Density 0.193%

numerical values followed by symbols or names related to programming or technology

specialized technical terms and identifiers related to programming or data management

No Comments

No Known Activations