INDEX

Explanations

information related to news and accidents involving a specific location

oai_token-act-pair · gpt-3.5-turbo

segments that indicate updates or announcements related to various topics

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

aukee

-0.74

 veter

-0.74

oun

-0.68

 awakening

-0.66

aturdays

-0.65

 submar

-0.64

 princ

-0.63

 surplus

-0.62

 Auditor

-0.62

 grandson

-0.61

POSITIVE LOGITS

Images

1.26

SOURCE

1.20

Featured

1.15

Thumbnail

1.14

Source

1.11

Via

1.09

via

1.06

Hat

1.04

advertising

1.03

Header

0.96

Activations Density 0.248%

information related to news and accidents involving a specific location

segments that indicate updates or announcements related to various topics

No Known Activations