INDEX

Explanations

phrases related to a specific number of days

oai_token-act-pair · gpt-3.5-turbo

references to time durations, specifically days and weeks

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

untled

-0.69

ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ

-0.68

 Thumbnails

-0.65

 horizont

-0.64

ifice

-0.63

Gra

-0.63

 enthusi

-0.62

 âĢº

-0.62

govtrack

-0.62

XT

-0.62

POSITIVE LOGITS

iversary

1.03

 anniversary

0.87

tenance

0.81

long

0.78

 turnaround

0.75

hold

0.70

 weekend

0.69

 affair

0.68

day

0.68

 evacuation

0.68

Activations Density 0.035%

phrases related to a specific number of days

references to time durations, specifically days and weeks

No Comments

No Known Activations