INDEX

Explanations

phrases related to politics, specifically mentions of the White House

oai_token-act-pair · gpt-3.5-turbo

references to the White House

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 exting

-1.02

 eleph

-0.95

 pione

-0.94

 practition

-0.91

Þ

-0.88

aditional

-0.88

 tremend

-0.87

 occas

-0.87

ò

-0.87

ortunately

-0.84

POSITIVE LOGITS

lace

0.47

forge

0.47

 Angeles

0.47

asury

0.47

ashington

0.46

leground

0.46

ennis

0.46

 Seed

0.45

 States

0.45

 Cabinet

0.44

Activations Density 0.131%

phrases related to politics, specifically mentions of the White House

references to the White House

No Comments

No Known Activations