INDEX

Explanations

phrases indicating the speaker's viewpoint or explanation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating opinions or assertions from various sources

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

cffffcc

-0.76

empt

-0.73

plug

-0.68

acts

-0.63

 enriched

-0.63

 bailed

-0.63

 acad

-0.63

riched

-0.63

 aven

-0.63

icates

-0.62

POSITIVE LOGITS

 Polly

0.73

 Compass

0.73

 historian

0.72

 Jonathan

0.71

NYT

0.70

 Stef

0.69

pace

0.69

 Mattis

0.68

 Joel

0.68

 Laura

0.68

Activations Density 0.049%

phrases indicating the speaker's viewpoint or explanation

phrases indicating opinions or assertions from various sources

No Comments

No Known Activations