INDEX

Explanations

topics related to slideshows or presentations

oai_token-act-pair · gpt-3.5-turbo

terms related to presentations and advisory roles

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

rie

-0.89

aling

-0.81

alities

-0.78

 Trin

-0.77

lez

-0.76

omy

-0.74

nai

-0.74

esy

-0.73

aled

-0.73

âĶģ

-0.73

POSITIVE LOGITS

 fixme

0.92

utherford

0.88

ï¸

0.84

ipolar

0.81

BIP

0.73

BILITIES

0.73

GGGGGGGG

0.73

qus

0.71

olicy

0.70

ELD

0.70

Activations Density 0.028%

topics related to slideshows or presentations

terms related to presentations and advisory roles

No Comments

No Known Activations