INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

specific names or identifiers related to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ashtra

-0.85

âĶĢâĶĢ

-0.84

;;;;;;;;;;;;

-0.78

imbabwe

-0.68

 Kinnikuman

-0.67

»Ĵ

-0.66

 Fidel

-0.66

Ö¼

-0.65

Pwr

-0.64

estic

-0.63

POSITIVE LOGITS

ricks

0.76

ãĤ±

0.76

ensen

0.76

reb

0.70

anson

0.68

enhagen

0.67

EStream

0.66

itz

0.66

udo

0.66

enberg

0.65

Activations Density 0.103%

names of individuals

specific names or identifiers related to individuals

No Comments

No Known Activations