INDEX

Explanations

numerical references to time periods

oai_token-act-pair · gpt-3.5-turbo

references to time increments and durations, particularly regarding changes or trends over specified periods

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

TextColor

-0.64

igham

-0.64

 scissors

-0.60

 leveled

-0.60

 insensitive

-0.59

 envy

-0.57

 Else

-0.57

Fine

-0.56

ogyn

-0.56

 scra

-0.55

POSITIVE LOGITS

th

1.00

 years

0.93

 months

0.86

teenth

0.85

yrs

0.82

century

0.81

imester

0.78

eteenth

0.77

years

0.76

months

0.74

Activations Density 0.068%

numerical references to time periods

references to time increments and durations, particularly regarding changes or trends over specified periods

No Comments

No Known Activations