INDEX

Explanations

abbreviations related to military equipment or technology

oai_token-act-pair · gpt-3.5-turbo

references to specific military technologies or systems, particularly related to THAAD (Terminal High Altitude Area Defense)

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ãĤŃ

-0.81

ãĤ±

-0.76

phis

-0.74

cloth

-0.73

etooth

-0.71

ãĤ¹ãĥĪ

-0.71

ãĥį

-0.70

detail

-0.69

ktop

-0.68

ãĥĥ

-0.68

POSITIVE LOGITS

OUGH

1.04

IRD

1.02

REE

0.88

ACK

0.88

ESE

0.87

INK

0.86

irteen

0.86

reads

0.86

OTAL

0.85

urst

0.84

Activations Density 0.008%

abbreviations related to military equipment or technology

references to specific military technologies or systems, particularly related to THAAD (Terminal High Altitude Area Defense)

No Comments

No Known Activations