INDEX

Explanations

dates in the format of years

oai_token-act-pair · gpt-3.5-turbo

references to numerical years, particularly those formatted as '20xx'

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

plom

-0.85

afort

-0.75

ablo

-0.73

pora

-0.69

kell

-0.68

hei

-0.68

uana

-0.67

etsk

-0.66

ãĥ£

-0.65

henko

-0.65

POSITIVE LOGITS

âĸĪâĸĪ

0.97

committee

0.85

th

0.85

oz

0.78

ISH

0.76

skirts

0.76

mph

0.75

SW

0.74

0.73

%"

0.73

Activations Density 0.056%

dates in the format of years

references to numerical years, particularly those formatted as '20xx'

No Comments

No Known Activations