INDEX

Explanations

phrases related to survey results and opinions

oai_token-act-pair · gpt-3.5-turbo

statistics and survey results related to public opinion

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arthed

-0.69

 racket

-0.69

missible

-0.68

 docking

-0.68

assetsadobe

-0.67

 scal

-0.65

????????

-0.65

 Hydra

-0.65

 starve

-0.64

 laundering

-0.64

POSITIVE LOGITS

 majorities

1.75

 Gallup

1.35

Pew

1.22

 polled

1.20

 respondents

1.15

 percentages

1.14

 polls

1.12

 plurality

1.08

 surveys

1.07

 poll

1.05

Activations Density 0.380%

phrases related to survey results and opinions

statistics and survey results related to public opinion

No Comments

No Known Activations