INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific end-of-text token

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

grass

-0.75

 Guinness

-0.72

 Nieto

-0.68

 Totem

-0.67

 Granger

-0.67

CPR

-0.66

 Dolphin

-0.65

 Sorceress

-0.65

Pom

-0.65

 daylight

-0.64

POSITIVE LOGITS

senal

1.32

ansom

1.19

ICH

1.18

outing

1.10

ascal

1.09

acing

1.08

abbit

1.07

agnar

1.07

outine

1.07

haps

1.07

Activations Density 0.031%

proper nouns

occurrences of a specific end-of-text token

No Comments

No Known Activations