INDEX

Explanations

references to specific locations, particularly focusing on cities and possibly legal facilities like jails

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographic locations, particularly those related to Native American context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

oeuv

-0.84

urst

-0.79

lass

-0.76

onut

-0.76

fare

-0.74

ramer

-0.74

lasses

-0.72

inse

-0.72

atures

-0.70

selage

-0.70

POSITIVE LOGITS

 Coyotes

0.92

ione

0.84

issance

0.80

 Navajo

0.80

DEN

0.75

AZ

0.74

endale

0.68

esan

0.68

 Wildcats

0.67

 Tucson

0.66

Activations Density 0.027%

references to specific locations, particularly focusing on cities and possibly legal facilities like jails

mentions of specific geographic locations, particularly those related to Native American context

No Comments

No Known Activations