INDEX

Explanations

phrases indicating uncertainty or speculation

oai_token-act-pair · gpt-3.5-turbo

conditional statements and expressions of uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

kefeller

-0.66

olini

-0.65

ipal

-0.58

 Hands

-0.56

 pione

-0.56

 Andersen

-0.55

 Citiz

-0.54

glers

-0.53

 Shots

-0.53

ãĤ¶

-0.52

POSITIVE LOGITS

1.17

1.14

!.

1.14

.[

1.12

.--

1.12

.(

1.08

;)

1.07

:)

1.06

.<

1.06

!,

1.04

Activations Density 0.599%

phrases indicating uncertainty or speculation

conditional statements and expressions of uncertainty

No Comments

No Known Activations