INDEX

Explanations

locations or directions

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

gey

-0.71

ynes

-0.70

 therein

-0.68

 Explain

-0.67

lain

-0.65

 contributors

-0.64

UFC

-0.62

 compares

-0.62

 compared

-0.61

ect

-0.60

POSITIVE LOGITS

 search

1.26

 handcuffs

1.19

dro

1.12

 haste

1.12

 pursuit

1.07

 disgust

1.03

 disguise

0.99

 desperation

0.92

 hopes

0.91

 tears

0.89

Activations Density 0.177%

locations or directions

the preposition "in" in various contexts

No Comments

No Known Activations