INDEX

Explanations

phrases related to time or durations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating duration or the concept of waiting

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nikov

-0.77

lesh

-0.71

emaker

-0.70

riad

-0.67

illard

-0.66

lar

-0.66

Always

-0.66

leck

-0.64

ror

-0.64

PLE

-0.63

POSITIVE LOGITS

ago

1.24

itud

1.12

 overdue

1.00

 awaited

0.94

itude

0.93

 periods

0.88

 lasting

0.86

Ago

0.80

 Term

0.79

velength

0.77

Activations Density 0.021%

phrases related to time or durations

phrases indicating duration or the concept of waiting

No Comments

No Known Activations