INDEX

Explanations

information related to specific event details like dates, locations, and participants

oai_token-act-pair · gpt-3.5-turbo

specific dates and locations related to events

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

 positives

-0.48

earchers

-0.42

 faint

-0.41

*/(

-0.41

 bats

-0.41

 meanwhile

-0.41

 survives

-0.40

 contradictory

-0.40

hematically

-0.40

paio

-0.40

POSITIVE LOGITS

 Junction

0.50

 Strait

0.46

Ely

0.46

ember

0.46

 Exhibition

0.45

 Albany

0.44

 Elys

0.44

 Quarter

0.44

Gw

0.43

 Trent

0.43

Activations Density 1.523%

information related to specific event details like dates, locations, and participants

specific dates and locations related to events

No Comments

No Known Activations