INDEX

Explanations

timestamps or specific days mentioned in sentences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "day."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

emort

-0.83

acus

-0.76

itars

-0.75

bourg

-0.75

icide

-0.73

umbn

-0.72

ocated

-0.72

cientious

-0.72

inav

-0.72

 externalToEVAOnly

-0.71

POSITIVE LOGITS

dream

1.31

days

0.84

DAY

0.81

day

0.79

long

0.78

 mornings

0.78

glass

0.77

flower

0.76

 morning

0.74

morrow

0.73

Activations Density 0.065%

timestamps or specific days mentioned in sentences

occurrences of the word "day."

No Comments

No Known Activations