INDEX

Explanations

words related to time, particularly references to the upcoming year

oai_token-act-pair · gpt-3.5-turbo

references to time periods, particularly the upcoming year

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

gotten

-0.91

esse

-0.69

uese

-0.66

ById

-0.65

nered

-0.64

-0.63

ocker

-0.62

apsed

-0.60

 anecd

-0.59

Dys

-0.59

POSITIVE LOGITS

 onwards

0.70

ruary

0.69

lins

0.68

mie

0.67

fw

0.66

Learn

0.66

0.65

iatus

0.65

å§«

0.64

cture

0.62

Activations Density 0.039%

words related to time, particularly references to the upcoming year

references to time periods, particularly the upcoming year

No Comments

No Known Activations