INDEX

Explanations

dates and locations described in a news context

oai_token-act-pair · gpt-3.5-turbo

locations and dates related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 hadn

-0.63

berman

-0.62

cox

-0.58

 wanted

-0.57

poon

-0.57

gotten

-0.57

 mortal

-0.57

idious

-0.57

BILITIES

-0.56

 Predator

-0.56

POSITIVE LOGITS

irtual

0.77

EVA

0.76

 Photographer

0.74

 incent

0.71

 REUTERS

0.70

 Photograph

0.70

UTERS

0.68

pei

0.67

 IMAGES

0.66

ember

0.64

Activations Density 0.241%

dates and locations described in a news context

locations and dates related to events

No Comments

No Known Activations