INDEX

Explanations

time-related phrases, specifically durations such as "two weeks" or "five years"

oai_token-act-pair · gpt-3.5-turbo

temporal references and time durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 fault

-0.81

 bluff

-0.68

ente

-0.66

aily

-0.65

incent

-0.63

 sympath

-0.63

 treadmill

-0.61

 incent

-0.60

 exhib

-0.60

 compuls

-0.60

POSITIVE LOGITS

 increments

0.98

 span

0.96

 nutshell

0.82

hops

0.78

ago

0.77

opian

0.77

 stride

0.77

inventoryQuantity

0.77

ixties

0.74

ruary

0.73

Activations Density 0.140%

time-related phrases, specifically durations such as "two weeks" or "five years"

temporal references and time durations

No Comments

No Known Activations