INDEX

Explanations

dates and time-related information

oai_token-act-pair · gpt-3.5-turbo

dates and times related to events or releases

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

itus

-0.80

odan

-0.77

anon

-0.77

manship

-0.76

zed

-0.73

vous

-0.71

umatic

-0.70

atics

-0.68

bart

-0.67

maxwell

-0.67

POSITIVE LOGITS

 theaters

0.94

 Hulu

0.83

 November

0.83

 February

0.79

 Deadline

0.79

 June

0.79

 December

0.78

 celebration

0.78

 commem

0.77

Activations Density 0.345%

dates and time-related information

dates and times related to events or releases

No Comments

No Known Activations