INDEX

Explanations

words related to durations of time

oai_token-act-pair · gpt-3.5-turbo

references to duration or length 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erala

-0.75

ramid

-0.72

 Cosponsors

-0.71

umo

-0.71

arte

-0.71

essor

-0.70

raised

-0.69

riad

-0.66

irlfriend

-0.66

racuse

-0.66

POSITIVE LOGITS

 lasting

1.05

 longer

0.82

 satisf

0.78

 pains

0.68

 uninterrupted

0.67

lasting

0.67

 veter

0.67

 months

0.67

Hours

0.66

 slee

0.66

Activations Density 0.028%

words related to durations of time

references to duration or length of time

No Comments

No Known Activations