INDEX

Explanations

phrases related to the name "Osso."

oai_token-act-pair · gpt-3.5-turbo

the word "so" and variations of it used in various contexts

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

 tracing

-0.65

 curves

-0.64

 deficit

-0.63

DERR

-0.63

 customs

-0.63

 triangle

-0.59

 indifference

-0.59

 homicide

-0.59

 prose

-0.59

 appra

-0.58

POSITIVE LOGITS

FTWARE

1.12

ppy

1.06

bered

1.04

oooo

1.03

othe

1.02

ll

1.02

ooo

1.01

vere

1.00

oner

0.99

fter

0.99

Activations Density 0.048%

phrases related to the name "Osso."

the word "so" and variations of it used in various contexts

No Comments

No Known Activations