INDEX

Explanations

keywords related to different modes or states of operation

oai_token-act-pair · gpt-3.5-turbo

references to different types of gameplay modes in a gaming context

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

Not in Any Lists

No Comments

Negative Logits

 Aires

-0.72

mony

-0.70

owan

-0.68

ammad

-0.68

alan

-0.66

areth

-0.65

rium

-0.65

ertodd

-0.65

enda

-0.64

atana

-0.63

POSITIVE LOGITS

 mode

0.90

mode

0.82

 modes

0.82

quit

0.82

etting

0.80

 Mode

0.74

 parity

0.71

 Modes

0.69

auga

0.67

 Shift

0.67

Activations Density 0.008%

keywords related to different modes or states of operation

references to different types of gameplay modes in a gaming context

No Comments

No Known Activations