INDEX

Explanations

prefixes or words containing "pred" followed by digits

oai_token-act-pair · gpt-3.5-turbo

words related to prediction and assumptions

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

ierrez

-0.72

ãĥīãĥ©ãĤ´ãĥ³

-0.70

Hub

-0.64

 Soup

-0.63

IFT

-0.62

ASE

-0.62

MENT

-0.61

uchi

-0.61

hiba

-0.61

HAEL

-0.59

POSITIVE LOGITS

efined

1.17

nis

0.99

icated

0.96

icates

0.94

icip

0.94

etermin

0.92

acent

0.92

awn

0.90

 pred

0.89

ominated

0.87

Activations Density 0.014%

prefixes or words containing "pred" followed by digits

words related to prediction and assumptions

No Comments

No Known Activations