INDEX

Explanations

phrases related to cause and effect

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate causal relationships or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

orn

-0.71

soDeliveryDate

-0.69

ELF

-0.67

quist

-0.66

IFIED

-0.66

OND

-0.65

HF

-0.64

ELD

-0.64

oph

-0.63

TERN

-0.63

POSITIVE LOGITS

 however

0.92

 moreover

0.82

 please

0.70

 coupled

0.69

 meanwhile

0.66

 namely

0.66

 chances

0.65

 assum

0.62

 whereby

0.62

dos

0.62

Activations Density 0.306%

phrases related to cause and effect

phrases that indicate causal relationships or conditions

No Comments

No Known Activations