INDEX

Explanations

military or law enforcement ranks and titles

oai_token-act-pair · gpt-3.5-turbo

military ranks and titles

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

 anew

-0.68

zsche

-0.66

anwhile

-0.65

entimes

-0.64

ahime

-0.63

ichever

-0.63

lessly

-0.62

otin

-0.61

 forged

-0.60

acles

-0.60

POSITIVE LOGITS

 Javier

1.02

 Jays

1.01

 Larry

1.01

 Jeffrey

1.00

 Brian

0.99

 Mike

0.99

 Gavin

0.98

 James

0.98

 Gary

0.97

 Timothy

0.97

Activations Density 0.050%

military or law enforcement ranks and titles

military ranks and titles

No Comments

No Known Activations