INDEX

Explanations

time durations expressed in weeks, months, hours, and other units

oai_token-act-pair · gpt-3.5-turbo

expressions of time duration, specifically comparing lengths of time

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

/#

-0.68

 facult

-0.62

ãĤ¨ãĥ«

-0.60

itor

-0.59

-0.57

###

-0.57

+)

-0.56

 monop

-0.55

++++

-0.55

untled

-0.54

POSITIVE LOGITS

 months

0.78

autical

0.78

 kilometres

0.74

 weeks

0.73

 hours

0.73

 miles

0.69

years

0.68

months

0.68

 seconds

0.68

inches

0.66

Activations Density 0.148%

time durations expressed in weeks, months, hours, and other units

expressions of time duration, specifically comparing lengths of time

No Comments

No Known Activations