INDEX

Explanations

phrases referring to parts or segments of a series, show, or program

oai_token-act-pair · gpt-3.5-turbo

references to episodes or parts of a series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

berus

-0.65

kefeller

-0.62

ministic

-0.60

ricanes

-0.59

gging

-0.56

anca

-0.56

 speakers

-0.56

 fluctuations

-0.56

urses

-0.56

urry

-0.56

POSITIVE LOGITS

icular

1.23

icles

1.19

icle

1.13

ners

1.12

ition

1.09

isans

1.05

nered

1.03

uary

1.02

ner

1.01

ridge

1.01

Activations Density 0.039%

phrases referring to parts or segments of a series, show, or program

references to episodes or parts of a series

No Comments

No Known Activations