INDEX

Explanations

words related to technology and specific product names

oai_token-act-pair · gpt-3.5-turbo

personal pronouns and references to individuals

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

advertisement

-0.72

glers

-0.66

 Romania

-0.58

 abdom

-0.58

 Poland

-0.58

 Typhoon

-0.58

ï¸ı

-0.58

 fungi

-0.57

 Myster

-0.57

ickr

-0.57

POSITIVE LOGITS

endment

0.91

assador

0.89

ICAN

0.82

lehem

0.81

pas

0.73

arella

0.71

ixture

0.71

angelo

0.68

hof

0.68

akeru

0.67

Activations Density 0.106%

words related to technology and specific product names

personal pronouns and references to individuals

No Comments

No Known Activations