INDEX

Explanations

updates or corrections in a story

oai_token-act-pair · gpt-3.5-turbo

references to stories, particularly updates and corrections related to them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

aez

-0.79

inence

-0.77

alus

-0.76

hammad

-0.75

ategory

-0.74

chwitz

-0.72

ensable

-0.72

retty

-0.71

achev

-0.70

ignt

-0.69

POSITIVE LOGITS

telling

1.04

 reprinted

0.91

 revolving

0.83

arc

0.81

icle

0.80

te

0.80

 headlined

0.80

 involving

0.79

 arcs

0.75

 relayed

0.74

Activations Density 0.050%

updates or corrections in a story

references to stories, particularly updates and corrections related to them

No Comments

No Known Activations