INDEX

Explanations

phrases related to network and computer systems

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "AD" followed by numerical values

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

Negative Logits

ĸļ

-0.97

ãĤ¡

-0.94

 Parenthood

-0.75

Ń·

-0.69

borough

-0.68

ãĥīãĥ©ãĤ´ãĥ³

-0.67

 Sturgeon

-0.67

 Kubrick

-0.66

htt

-0.66

ãĤ©

-0.66

POSITIVE LOGITS

VERTISEMENT

1.35

vantage

1.04

venture

0.95

VERTIS

0.95

MIN

0.90

iamond

0.88

JECT

0.87

visor

0.85

DI

0.84

vance

0.83

Activations Density 0.007%

phrases related to network and computer systems

occurrences of the term "AD" followed by numerical values

No Known Activations