INDEX

Explanations

phrases starting with the word "Wh"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the substring "Wh"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WARE

-0.79

phrine

-0.79

uated

-0.76

ATIONS

-0.73

uating

-0.70

Reloaded

-0.70

DEN

-0.70

 Blazers

-0.68

steen

-0.66

KEN

-0.65

POSITIVE LOGITS

istle

1.25

ilst

1.25

olly

1.22

irlwind

1.21

ispers

1.15

isky

1.08

atson

1.07

soever

1.07

ither

1.02

izz

1.02

Activations Density 0.011%

phrases starting with the word "Wh"

occurrences of the substring "Wh"

No Comments

No Known Activations