INDEX

Explanations

expressions related to time durations

oai_token-act-pair · gpt-3.5-turbo

references to numbers, particularly relating to quantities and durations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

akov

-0.73

 himself

-0.73

rogens

-0.69

 herself

-0.68

utes

-0.68

 myself

-0.66

arov

-0.66

rary

-0.65

actly

-0.64

rett

-0.64

POSITIVE LOGITS

 foray

1.25

 flagship

0.99

 namesake

0.95

 headquarters

0.93

 holdings

0.91

 woes

0.84

 motto

0.83

own

0.82

nem

0.82

 mascot

0.80

Activations Density 0.306%

expressions related to time durations

references to numbers, particularly relating to quantities and durations

No Comments

No Known Activations