INDEX

Explanations

the word "Knight"

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the name "Knight."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

mble

-0.78

ional

-0.74

andem

-0.73

ience

-0.73

ascus

-0.73

iversal

-0.73

imester

-0.72

etsk

-0.72

ential

-0.70

obos

-0.68

POSITIVE LOGITS

 Templar

1.23

mare

1.22

 Knight

1.16

holder

1.06

mares

1.06

 Riders

0.95

 Knights

0.94

 Rider

0.93

fish

0.91

 Templ

0.89

Activations Density 0.011%

the word "Knight"

repeated mentions of the name "Knight."

No Comments

No Known Activations