INDEX

Explanations

references to intensity or high levels of something

oai_token-act-pair · gpt-3.5-turbo

the word "Int" and its variations or related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Gleaming

-0.76

wagen

-0.70

hyde

-0.68

 palms

-0.68

¶ħ

-0.67

pees

-0.65

baum

-0.62

awaru

-0.61

pee

-0.61

 lions

-0.60

POSITIVE LOGITS

ensive

1.28

ention

1.28

ellect

1.27

ensity

1.19

ellig

1.14

estinal

1.10

ENTION

1.08

ensions

1.06

angible

1.05

rast

1.04

Activations Density 0.028%

references to intensity or high levels of something

the word "Int" and its variations or related forms

No Comments

No Known Activations