INDEX

Explanations

release dates mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

terms related to release dates

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

ided

-0.87

ricular

-0.80

obe

-0.80

oyd

-0.80

arus

-0.79

igent

-0.78

ateral

-0.78

roph

-0.78

ritch

-0.75

htaking

-0.75

POSITIVE LOGITS

 date

0.84

 dates

0.80

TBD

0.80

 Dates

0.75

dates

0.73

0.71

 Countdown

0.68

0.67

tenance

0.67

âĢİ

0.66

Activations Density 0.016%

release dates mentioned in the text

terms related to release dates

No Comments

No Known Activations