INDEX

Explanations

phrases related to durations of time

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "day" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

idges

-0.78

ethical

-0.73

ashtra

-0.73

itars

-0.71

icides

-0.70

asc

-0.69

ifice

-0.69

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.69

estern

-0.68

inates

-0.68

POSITIVE LOGITS

dream

1.15

light

0.85

lights

0.84

long

0.80

day

0.78

lihood

0.78

noon

0.76

moon

0.75

 Advent

0.72

theless

0.72

Activations Density 0.038%

phrases related to durations of time

occurrences of the word "day" in various contexts

No Comments

No Known Activations