INDEX

Explanations

dates expressed with a day number followed by the name of a month

oai_token-act-pair · gpt-3.5-turbo

references to specific dates across various contexts

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

 looph

-0.71

 predec

-0.70

mercial

-0.69

 princ

-0.66

keyes

-0.65

 proble

-0.65

kef

-0.65

 heirs

-0.64

atem

-0.64

 arrang

-0.64

POSITIVE LOGITS

0.97

0.96

0.91

0.86

0.85

0.83

0.81

0.80

Activations Density 0.093%

dates expressed with a day number followed by the name of a month

references to specific dates across various contexts

No Comments

No Known Activations