INDEX

Explanations

references to spans of time, particularly in number form

oai_token-act-pair · gpt-3.5-turbo

numerical values representing quantities or durations

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

 abbre

-0.66

 Caption

-0.65

 moderator

-0.64

rike

-0.64

 turnout

-0.61

ashtra

-0.60

 Ahead

-0.58

encer

-0.57

imaru

-0.56

llor

-0.55

POSITIVE LOGITS

 years

1.11

 weeks

1.07

 months

1.05

 generations

1.02

 decades

0.99

 consecutive

0.98

 days

0.98

months

0.97

 minutes

0.97

 hours

0.96

Activations Density 0.180%

references to spans of time, particularly in number form

numerical values representing quantities or durations

No Comments

No Known Activations