INDEX

Explanations

names or titles of important figures or characters

oai_token-act-pair · gpt-3.5-turbo

titles and roles associated with important figures or characters in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enture

-0.63

entimes

-0.63

 skirm

-0.63

aurus

-0.62

wcsstore

-0.62

lander

-0.60

ciplinary

-0.59

INFO

-0.59

 Pradesh

-0.59

Draft

-0.58

POSITIVE LOGITS

 Theo

1.15

 Ezra

1.11

 Sonny

1.11

 Gina

1.11

 Emil

1.10

 Andrew

1.10

 Christine

1.09

 Steph

1.09

 Liam

1.09

 Pierre

1.08

Activations Density 0.290%

names or titles of important figures or characters

titles and roles associated with important figures or characters in narratives

No Comments

No Known Activations