INDEX

Explanations

words related to the location "Fremont"

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lihood

-0.77

draw

-0.76

 Cassidy

-0.73

Beg

-0.68

 Gerry

-0.65

lift

-0.64

 Paige

-0.64

library

-0.62

 Izan

-0.61

gio

-0.59

POSITIVE LOGITS

antle

1.36

 Frem

0.94

actory

0.93

cipled

0.83

puter

0.83

ilit

0.83

asonry

0.79

inite

0.79

rament

0.78

ont

0.78

Activations Density 0.006%

words related to the location "Fremont"

proper nouns, specifically names of people and places

No Comments

No Known Activations