INDEX

Explanations

proper nouns related to locations or entities containing the letter "G"

oai_token-act-pair · gpt-3.5-turbo

references to a specific entity or concept represented by "G"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĸļ

-0.69

terday

-0.68

oÄŁ

-0.65

htt

-0.64

puter

-0.63

 Conquest

-0.63

 retrospect

-0.63

 craw

-0.62

 derail

-0.62

 Crusher

-0.62

POSITIVE LOGITS

reet

1.19

reetings

1.13

oliath

1.13

asp

1.13

ourmet

1.12

irlfriend

1.12

ossip

1.12

CHQ

1.11

ospels

1.08

iant

1.07

Activations Density 0.048%

proper nouns related to locations or entities containing the letter "G"

references to a specific entity or concept represented by "G"

No Comments

No Known Activations