INDEX

Explanations

phrases related to news reports or updates

oai_token-act-pair · gpt-3.5-turbo

occurrences of unspecified significant events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Artemis

-0.68

UX

-0.66

 Voyager

-0.65

 Experience

-0.65

 Vend

-0.65

 Vision

-0.65

 diving

-0.64

 endeavour

-0.64

Aeg

-0.63

 util

-0.63

POSITIVE LOGITS

Posted

1.68

advertisement

1.48

posted

1.42

ÂłÂłÂłÂłÂłÂłÂłÂł

1.36

RAW

1.29

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

1.27

Article

1.24

ÂłÂłÂłÂł

1.21

ÂłÂłÂł

1.16

ÂłÂł

1.04

Activations Density 0.339%

phrases related to news reports or updates

occurrences of unspecified significant events or actions

No Comments

No Known Activations