INDEX

Explanations

phrases related to long durations of time

oai_token-act-pair · gpt-3.5-turbo

references to durations specifically measured in "long" periods of time

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

onom

-0.79

icket

-0.75

ulkan

-0.73

Peb

-0.69

Earth

-0.68

ku

-0.68

osponsors

-0.67

 Allaah

-0.67

 Tickets

-0.66

ARCH

-0.66

POSITIVE LOGITS

 ordeal

0.86

ago

0.86

tir

0.82

 deliberations

0.80

 operation

0.79

 uninterrupted

0.78

rontal

0.78

 hiatus

0.78

 correspondence

0.77

 slog

0.77

Activations Density 0.026%

phrases related to long durations of time

references to durations specifically measured in "long" periods of time

No Comments

No Known Activations