INDEX

Explanations

references related to political figures and their activities

oai_token-act-pair · gpt-3.5-turbo

references to political debates and their key moments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

LTD

-0.95

conservancy

-0.80

 envis

-0.79

velop

-0.78

 Pione

-0.75

 colony

-0.74

byss

-0.72

ffect

-0.72

 colonies

-0.71

knit

-0.70

POSITIVE LOGITS

 MSNBC

1.35

 Hannity

1.17

 CNBC

1.17

 rant

1.16

 comedian

1.15

 comedians

1.13

CNN

1.11

 commentator

1.10

 interviewer

1.07

 onstage

1.07

Activations Density 1.448%

references related to political figures and their activities

references to political debates and their key moments

No Comments

No Known Activations