INDEX

Explanations

words related to filmmaking and movie-related terms

oai_token-act-pair · gpt-3.5-turbo

references to the word "Fil" or its variations

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

anwhile

-0.76

è¦ļéĨĴ

-0.72

 compr

-0.69

ELL

-0.67

 Butterfly

-0.66

schild

-0.65

 convict

-0.64

 digest

-0.63

eanor

-0.62

JV

-0.62

POSITIVE LOGITS

tered

1.19

ters

1.17

igree

1.06

tering

1.05

thy

1.02

terness

0.98

eno

0.94

fil

0.93

Fil

0.92

teenth

0.91

Activations Density 0.009%

words related to filmmaking and movie-related terms

references to the word "Fil" or its variations

No Comments

No Known Activations